Search

Given a row-finite higher-rank $k$-graph $\Lambda$, we define a commutative monoid $T_\Lambda$ which is a higher-rank analogue of the talented monoid of a directed graph. The talented monoid $T_\Lambda$ is canonically a $\mathbb{Z}^k$-monoid with respect to the action of state shift. This monoid coincides with the positive cone of the graded Grothendieck group $K_0^{gr}(KP_\mathsf{k}(\Lambda))$ of the Kumjian-Pask algebra $KP_\mathsf{k}(\Lambda)$ with coefficients in a field $\mathsf{k}$. The aim of the paper is to investigate this $\mathbb{Z}^k$-monoid as a capable invariant for classification of Kumjian-Pask algebras. If $\mathbb{Z}^k$ acts freely on $T_\Lambda$ (i.e., if $T_\Lambda$ has no nonzero periodic element), then we show that the $k$-graph $\Lambda$ is aperiodic. The converse is also proved to be true provided $\Lambda$ has no sources and $T_\Lambda$ is atomic. Moreover in this case, we provide a talented monoid characterization for strongly aperiodic $k$-graphs. We prove that for a row-finite $k$-graph $\Lambda$ without sources, cofinality is equivalent to the simplicity of $T_\Lambda$ as a $\mathbb{Z}^k$-monoid. In view of this we provide a talented monoid criterion for the Kumjian-Pask algebra $KP_R(\Lambda)$ of $\Lambda$ over a unital commutative ring $R$ to be graded basic ideal simple. We also describe the minimal left ideals of $KP_\mathsf{k}(\Lambda)$ in terms of the aperiodic atoms of $T_\Lambda$ and thus obtain a monoid theoretic characterization for $Soc(KP_\mathsf{k}(\Lambda)$) to be an essential ideal. These results help us to characterize semisimple Kumjian-Pask algebras through the lens of $T_\Lambda$.

We prove what might have been expected: The Williams Conjecture in symbolic dynamics and Graded Morita Equivalence Conjecture for Leavitt/$C^*$-graph algebras hold for ``small graphs'', i.e., connected graphs with three vertices, no parallel edges, no sinks with no trivial hereditary and saturated subsets. Namely, two small graphs are shift equivalent if and only if they are strong shift equivalent if and only if their Leavitt/$C^*$-graph algebras are graded/equivariant Morita equivalent., Comment: 33 pages

Non-linear convection-reaction-diffusion (CRD) partial differential equations (PDEs) are crucial for modeling complex phenomena in fields such as biology, ecology, population dynamics, physics, and engineering. Numerical approximation of these non-linear systems is essential due to the challenges of obtaining exact solutions. Traditionally, the Galerkin finite element method (GFEM) has been the standard computational tool for solving these PDEs. With the advancements in machine learning, Physics-Informed Neural Network (PINN) has emerged as a promising alternative for approximating non-linear PDEs. In this study, we compare the performance of PINN and GFEM by solving four distinct one-dimensional CRD problems with varying initial and boundary conditions and evaluate the performance of PINN over GFEM. This evaluation metrics includes error estimates, and visual representations of the solutions, supported by statistical methods such as the root mean squared error (RMSE), the standard deviation of error, the the Wilcoxon Signed-Rank Test and the coefficient of variation (CV) test. Our findings reveal that while both methods achieve solutions close to the analytical results, PINN demonstrate superior accuracy and efficiency. PINN achieved significantly lower RMSE values and smaller standard deviations for Burgers' equation, Fisher's equation, and Newell-Whitehead-Segel equation, indicating higher accuracy and greater consistency. While GFEM shows slightly better accuracy for the Burgers-Huxley equation, its performance was less consistent over time. In contrast, PINN exhibit more reliable and robust performance, highlighting their potential as a cutting-edge approach for solving non-linear PDEs., Comment: 29 pages, 13 figures

Applying deep learning (DL) for annotating surgical instruments in robot-assisted minimally invasive surgeries (MIS) represents a significant advancement in surgical technology. This systematic review examines 48 studies that and advanced DL methods and architectures. These sophisticated DL models have shown notable improvements in the precision and efficiency of detecting and segmenting surgical tools. The enhanced capabilities of these models support various clinical applications, including real-time intraoperative guidance, comprehensive postoperative evaluations, and objective assessments of surgical skills. By accurately identifying and segmenting surgical instruments in video data, DL models provide detailed feedback to surgeons, thereby improving surgical outcomes and reducing complication risks. Furthermore, the application of DL in surgical education is transformative. The review underscores the significant impact of DL on improving the accuracy of skill assessments and the overall quality of surgical training programs. However, implementing DL in surgical tool detection and segmentation faces challenges, such as the need for large, accurately annotated datasets to train these models effectively. The manual annotation process is labor-intensive and time-consuming, posing a significant bottleneck. Future research should focus on automating the detection and segmentation process and enhancing the robustness of DL models against environmental variations. Expanding the application of DL models across various surgical specialties will be essential to fully realize this technology's potential. Integrating DL with other emerging technologies, such as augmented reality (AR), also offers promising opportunities to further enhance the precision and efficacy of surgical procedures., Comment: 57 pages, 9 figures, Published in Artificial Intelligence Reviews journal

The Graded Classification Conjecture states that for finite directed graphs $E$ and $F$, the associated Leavitt path algebras $L_\K(E)$ and $L_\K(F)$ are graded Morita equivalent, i.e., $\Gr L_\K(E) \approx_{\gr} \Gr L_\K(F)$, if and only if, their graded Grothendieck groups are isomorphic $K_0^{\gr}(L_\K(E)) \cong K_0^{\gr}(L_\K(F))$ as order-preserving $\mathbb Z[x,x^{-1}]$-modules. Furthermore, if under this isomorphism, the class $[L_\K(E)]$ is sent to $[L_\K(F)]$ then the algebras are graded isomorphic, i.e., $L_\K(E) \cong _{\gr} L_\K(F)$. In this note we show that, for finite graphs $E$ and $F$ with so sinks and sources, an order-preserving $\mathbb Z[x,x^{-1}]$-module isomorphism $K_0^{\gr}(L_\K(E)) \cong K_0^{\gr}(L_\K(F))$ gives that the categories of locally finite dimensional graded modules of $L_\K(E)$ and $L_\K(F)$ are equivalent, i.e., $\fGr[\mathbb{Z}] L_\K(E)\approx_{\gr} \fGr[\mathbb{Z}]L_\K(F).$ We further obtain that the category of finite dimensional (graded) modules are equivalent, i.e., $\fModd L_\K(E) \approx \fModd L_\K(F)$ and $\fGr L_\K(E) \approx_{\gr} \fGr L_\K(F)$.

We prove that a unital shift equivalence induces a graded isomorphism of Leavitt path algebras when the shift equivalence satisfies an alignment condition. This yields another step towards confirming the Graded Classification Conjecture. Our proof uses the bridging bimodule developed by Abrams, the fourth-named author and Tomforde, as well as a general lifting result for graded rings that we establish here. This general result also allows us to provide simplified proofs of two important recent results: one independently proven by Arnone and Va{\v s} through other means that the graded $K$-theory functor is full, and the other proven by Arnone and Corti\~nas that there is no unital graded homomorphism between a Leavitt algebra and the path algebra of a Cuntz splice., Comment: v2. 14 pages, added Remark 5.3

Leavitt path algebras, which are algebras associated to directed graphs, were first introduced about 20 years ago. They have strong connections to such topics as symbolic dynamics, operator algebras, non-commutative geometry, representation theory, and even chip firing. In this article we invite the reader to sneak a peek at these fascinating algebras and their interplay with several seemingly disparate parts of mathematics.

Recent developments in multimodal large language models (MLLMs) have spurred significant interest in their potential applications across various medical imaging domains. On the one hand, there is a temptation to use these generative models to synthesize realistic-looking medical image data, while on the other hand, the ability to identify synthetic image data in a pool of data is also significantly important. In this study, we explore the potential of the Gemini (\textit{gemini-1.0-pro-vision-latest}) and GPT-4V (gpt-4-vision-preview) models for medical image analysis using two modalities of medical image data. Utilizing synthetic and real imaging data, both Gemini AI and GPT-4V are first used to classify real versus synthetic images, followed by an interpretation and analysis of the input images. Experimental results demonstrate that both Gemini and GPT-4 could perform some interpretation of the input images. In this specific experiment, Gemini was able to perform slightly better than the GPT-4V on the classification task. In contrast, responses associated with GPT-4V were mostly generic in nature. Our early investigation presented in this work provides insights into the potential of MLLMs to assist with the classification and interpretation of retinal fundoscopy and lung X-ray images. We also identify key limitations associated with the early investigation study on MLLMs for specialized tasks in medical image analysis., Comment: Accepted in Fifth IEEE Workshop on Artificial Intelligence for HealthCare, IEEE 25th International Conference on Information Reuse and Integration for Data Science

We investigate the behavior of various measures of quantum coherence and quantum correlation in the spin-1/2 Heisenberg XYZ model with added Dzyaloshinsky-Moriya (DM) and Kaplan--Shekhtman--Entin-Wohlman--Aharony (KSEA) interactions at a thermal regime described by a Gibbs density operator. We aim to understand the restricted hierarchical classification of different quantum resources, where Bell nonlocality $\subseteq$ quantum steering $\subseteq$ quantum entanglement $\subseteq$ quantum discord $\subseteq$ quantum coherence. This hierarchy highlights the increasingly stringent conditions required as we move from quantum coherence to more specific quantum phenomena. In order to enhance quantum coherence, quantum correlation, and fidelity of teleportation, our analysis encompasses the effects of independently provided sinusoidal magnetic field control as well as DM and KSEA interactions on the considered system. The results reveal that enhancing the entanglement or quantum correlation of the channel does not always guarantee successful teleportation or even an improvement in teleportation fidelity. Thus, the relationship between teleportation fidelity and the channel's underlying quantum properties is intricate. Our study provides valuable insights into the complex interplay of quantum coherence and correlation hierarchy, offering potential applications for quantum communication and information processing technologies., Comment: 12 pages, 4 figures. All comments are welcome

We propose a scheme for the generation of nonreciprocal multipartite entanglement in a two-mode cavity magnomechanical system, consisting of two cross microwave (MW) cavities having an yttrium iron garnet (YIG) sphere, which is coupled through magnetic dipole interaction. Our results show that the magnon self-Kerr effect can significantly enhance bipartite entanglement, which turns out to be non-reciprocal when the magetic field is tuned along the crystallographic axis [110]. This is due to the frequency shift on the magnons (YIG sphere), which depends upon the direction of magnetic field. Interestingly, the degree of nonreciprocity of entanglement depends upon a careful optimal choice of system parameters like normalizd cavity detunings, bipartite nonlinear index $\Delta E_{K}$, self-Kerr coefficient and effective magnomechanical coupling rate $G$. In addition to bipartite entanglement, we also explored the nonreciprocity in tripartite entanglement. Our present theoretical proposal for nonreciprocity in multipartite entanglement may find applications in diverse engineering nonreciprocal devices., Comment: 11 pages, 7figures

In this paper, we analytically present the phenomena of nanomechanically induced transparency (NMIT) and transmission rate in a parity-time-symmetric ($\mathcal{PT}$-symmetric) opto-nanomechanical system (ONMS) where a levitated dielectric nanospheres is trapped near the antinodes closest to right mirror of passive cavity which further coupled to an active cavity via hoping factor. We find that the phenomenon of NMIT may be generated from the output probe field in the presence of an effective opto-nanomechanical coupling between the cavity field and the nanosphere, whose steady-state position is influenced by the Coulomb interaction between the cavity mirror and the nanosphere. In addition, the width and height of the transparency window can be controlled through the effective optomechanical coupling, which is readily adjusted by altering changing the nanosphere's radius and the Coulomb interaction. One of the most interesting result is the transition NMIT behavior in $\mathcal{PT}$-symmetric and broken $\mathcal{PT}$-symmetric regime. We show that the presence of nanosphere in the passive cavity enhances the width and transmission rate of NMIT window in passive-passive regime and in passive-active regime, a notable decrease of sideband amplification has been observed. These results show that our scheme may find some potential applications for optical signal processing an and quantum information processing., Comment: 7 pages, 6 figures

A half a century ago, George Bergman introduced stunning machinery which would realise any commutative conical monoid as the non-stable $K$-theory of a ring. The ring constructed is ``minimal" or ``universal". Given the success of graded $K$-theory in classification of algebras and its connections to dynamics and operator algebras, the realisation of $\Gamma$-monoids (monoids with an action of an abelian group $\Gamma$ on them) as non-stable graded $K$-theory of graded rings becomes vital. In this paper, we revisit Bergman's work and develop the graded version of this universal construction. For an abelian group $\Gamma$, a $\Gamma$-graded ring $R$, and non-zero graded finitely generated projective (left) $R$-modules $P$ and $Q$, we construct a universal $\Gamma$-graded ring extension $S$ such that $S\otimes_R P\cong S\otimes_R Q$ as graded $S$-modules. This makes it possible to bring the graded techniques, such as smash products and Zhang twists into Bergman's machinery. Given a commutative conical $\Gamma$-monoid $M$, we construct a $\Gamma$-graded ring $S$ such that $\mathcal V^{gr}(S)$ is $\Gamma$-isomorphic to $M$. In fact we show that any finitely generated $\Gamma$-monoid can be realised as the non-stable graded $K$-theory of a hyper Leavitt path algebra. Here $\mathcal V^{gr}(S)$ is the monoid of isomorphism classes of graded finitely generated projective $S$-modules and the action of $\Gamma$ on $\mathcal V^{gr}(S)$ is by shift of degrees. Thus the group completion of $M$ can be realised as the graded Grothendieck group $K^{\gr}_0(S)$. We use this machinery to provide a short proof to the fullness of the graded Grothendieck functor $K^{gr}_0$ for the class of Leavitt path algebras (i.e., Graded Classification Conjecture II)., Comment: Comments and corrections are very welcome!

The theory of Leavitt path algebras is intrinsically related, via graphs, to the theory of symbolic dynamics and $C^*$-algebras where the major classification programs have been a domain of intense research in the last 50 years. In this survey article, we gather together current lines of research in the classification of Leavitt path algebras, questions, conjectures, and some of the results about them that have been obtained so far., Comment: Final version

In this article, we describe the endomorphism ring of a finitely generated progenerator module of a weighted Leavitt path algebra $L_{K}(E, w)$ of a finite vertex weighted graph $(E, w)$. Contrary to the case of Leavitt path algebras, we show that a (full) corner of a weighted Leavitt path algebra is, in general, not isomorphic to a weighted Leavitt path algebra. However, using the above result, we show that for every full idempotent $\epsilon$ in $L_{K}(E, w)$, there exists a positive integer $n$ such that $M_n(\epsilon L_{K}(E, w) \epsilon)$ is isomorphic to the weighted Leavitt path algebra of a weighted graph explicitly constructed from $(E, w)$. We then completely describe unital algebras being Morita equivalent to weighted Leavitt path algebras of vertex weighted graphs. In particular, we characterize unital algebras being Morita equivalent to sandpile algebras.

Several deep learning algorithms have shown amazing performance for existing object detection tasks, but recognizing darker objects is the largest challenge. Moreover, those techniques struggled to detect or had a slow recognition rate, resulting in significant performance losses. As a result, an improved and accurate detection approach is required to address the above difficulty. The whole study proposes a combination of spiked and normal convolution layers as an energy-efficient and reliable object detector model. The proposed model is split into two sections. The first section is developed as a feature extractor, which utilizes pre-trained VGG16, and the second section of the proposal structure is the combination of spiked and normal Convolutional layers to detect the bounding boxes of images. We drew a pre-trained model for classifying detected objects. With state of the art Python libraries, spike layers can be trained efficiently. The proposed spike convolutional object detector (SCOD) has been evaluated on VOC and Ex-Dark datasets. SCOD reached 66.01% and 41.25% mAP for detecting 20 different objects in the VOC-12 and 12 objects in the Ex-Dark dataset. SCOD uses 14 Giga FLOPS for its forward path calculations. Experimental results indicated superior performance compared to Tiny YOLO, Spike YOLO, YOLO-LITE, Tinier YOLO and Center of loc+Xception based on mAP for the VOC dataset.

Vision transformer-based methods are advancing the field of medical artificial intelligence and cancer imaging, including lung cancer applications. Recently, many researchers have developed vision transformer-based AI methods for lung cancer diagnosis and prognosis. This scoping review aims to identify the recent developments on vision transformer-based AI methods for lung cancer imaging applications. It provides key insights into how vision transformers complemented the performance of AI and deep learning methods for lung cancer. Furthermore, the review also identifies the datasets that contributed to advancing the field. Of the 314 retrieved studies, this review included 34 studies published from 2020 to 2022. The most commonly addressed task in these studies was the classification of lung cancer types, such as lung squamous cell carcinoma versus lung adenocarcinoma, and identifying benign versus malignant pulmonary nodules. Other applications included survival prediction of lung cancer patients and segmentation of lungs. The studies lacked clear strategies for clinical transformation. SWIN transformer was a popular choice of the researchers; however, many other architectures were also reported where vision transformer was combined with convolutional neural networks or UNet model. It can be concluded that vision transformer-based models are increasingly in popularity for developing AI methods for lung cancer applications. However, their computational complexity and clinical relevance are important factors to be considered for future research work. This review provides valuable insights for researchers in the field of AI and healthcare to advance the state-of-the-art in lung cancer diagnosis and prognosis. We provide an interactive dashboard on lung-cancer.onrender.com/., Comment: submitted to BMC Medical Imaging journal

The purpose of the research is to find the numerical solutions to the system of time dependent nonlinear parabolic partial differential equations (PDEs) utilizing the Modified Galerkin Weighted Residual Method (MGWRM) with the help of modified Bernstein polynomials. An approximate solution of the system has been assumed in accordance with the modified Bernstein polynomials. Thereafter, the modified Galerkin method has been applied to the system of nonlinear parabolic PDEs and has transformed the model into a time dependent ordinary differential equations system. Then the system has been converted into the recurrence equations by employing backward difference approximation. However, the iterative calculation is performed by using the Picard Iterative method. A few renowned problems are then solved to test the applicability and efficiency of our proposed scheme. The numerical solutions at different time levels are then displayed numerically in tabular form and graphically by figures. The comparative study is presented along with L2 norm, and L infinity norm.

A meteor graph is a connected graph with no sources and sinks consisting of two disjoint cycles and the paths connecting these cycles. We prove that two meteor graphs are shift equivalent if and only if they are strongly shift equivalent, if and only if their corresponding Leavitt path algebras are graded Morita equivalent, if and only if their graded $K$-theories, $K_0^{gr}$, are $\mathbb Z [x,x^{-1}]$-module isomorphic. As a consequence, the Leavitt path algebras of meteor graphs are graded Morita equivalent if and only if their graph $C^*$-algebras are equivariant Morita equivalent., Comment: 27 pages, comments are welcome!

Artificial Intelligence (AI)-based models can help in diagnosing COVID-19 from lung CT scans and X-ray images; however, these models require large amounts of data for training and validation. Many researchers studied Generative Adversarial Networks (GANs) for producing synthetic lung CT scans and X-Ray images to improve the performance of AI-based models. It is not well explored how good GAN-based methods performed to generate reliable synthetic data. This work analyzes 43 published studies that reported GANs for synthetic data generation. Many of these studies suffered data bias, lack of reproducibility, and lack of feedback from the radiologists or other domain experts. A common issue in these studies is the unavailability of the source code, hindering reproducibility. The included studies reported rescaling of the input images to train the existing GANs architecture without providing clinical insights on how the rescaling was motivated. Finally, even though GAN-based methods have the potential for data augmentation and improving the training of AI-based models, these methods fall short in terms of their use in clinical practice. This paper highlights research hotspots in countering the data scarcity problem, identifies various issues as well as potentials, and provides recommendations to guide future research. These recommendations might be useful to improve acceptability for the GAN-based approaches for data augmentation as GANs for data augmentation are increasingly becoming popular in the AI and medical imaging research community., Comment: submitted to 2023 CVPR workshop on Generative Models for Computer Vision

In this article, we substantiate the appositeness of the \emph{mode-matching technique} to study the scattering response of bridging elastic plates connecting two flexible duct regions of different heights. We present two different solution schemes to analyze the structure-borne and fluid-borne radiations in the elastic plate-bounded waveguide. The first scheme supplements the mode-matching technique with the so-called \emph{tailored-Galerkin approach} which uses a solution ansatz with homogeneous and integral parts corresponding to the vibrations of the bridging elastic plate and the cavity, respectively. In the second scheme, we supplement the mode-matching technique with the \emph{modal approach} wherein the displacement of the bridging elastic plate is projected onto the eigenmodes of the cavity. To handle the non-orthogonality of the eigenfunctions, we invoke generalized orthogonality relations. An advantage of the proposed mode-matching schemes is that they provide a convenient way of incorporating a variety of edge conditions on the joints of the plates, including clamped, pin-joint, or restraint connections. The numerical analysis of the waveguide scattering problems substantiates that edge connections on the joints have a significant impact on the scattering energies and transmission loss., Comment: 27 pages, 5 figures

Generative models have been very successful over the years and have received significant attention for synthetic data generation. As deep learning models are getting more and more complex, they require large amounts of data to perform accurately. In medical image analysis, such generative models play a crucial role as the available data is limited due to challenges related to data privacy, lack of data diversity, or uneven data distributions. In this paper, we present a method to generate brain tumor MRI images using generative adversarial networks. We have utilized StyleGAN2 with ADA methodology to generate high-quality brain MRI with tumors while using a significantly smaller amount of training data when compared to the existing approaches. We use three pre-trained models for transfer learning. Results demonstrate that the proposed method can learn the distributions of brain tumors. Furthermore, the model can generate high-quality synthetic brain MRI with a tumor that can limit the small sample size issues. The approach can addresses the limited data availability by generating realistic-looking brain MRI with tumors. The code is available at: ~\url{https://github.com/rizwanqureshi123/Brain-Tumor-Synthetic-Data}., Comment: Accepted in AICS conference

Generative models are becoming popular for the synthesis of medical images. Recently, neural diffusion models have demonstrated the potential to generate photo-realistic images of objects. However, their potential to generate medical images is not explored yet. In this work, we explore the possibilities of synthesis of medical images using neural diffusion models. First, we use a pre-trained DALLE2 model to generate lungs X-Ray and CT images from an input text prompt. Second, we train a stable diffusion model with 3165 X-Ray images and generate synthetic images. We evaluate the synthetic image data through a qualitative analysis where two independent radiologists label randomly chosen samples from the generated data as real, fake, or unsure. Results demonstrate that images generated with the diffusion model can translate characteristics that are otherwise very specific to certain medical conditions in chest X-Ray or CT images. Careful tuning of the model can be very promising. To the best of our knowledge, this is the first attempt to generate lungs X-Ray and CT images using neural diffusion models. This work aims to introduce a new dimension in artificial intelligence for medical imaging. Given that this is a new topic, the paper will serve as an introduction and motivation for the research community to explore the potential of diffusion models for medical image synthesis. We have released the synthetic images on https://www.kaggle.com/datasets/hazrat/awesomelungs., Comment: 8 pages. Submitted to AICS 2022 conference

Healthcare data are inherently multimodal, including electronic health records (EHR), medical images, and multi-omics data. Combining these multimodal data sources contributes to a better understanding of human health and provides optimal personalized healthcare. Advances in artificial intelligence (AI) technologies, particularly machine learning (ML), enable the fusion of these different data modalities to provide multimodal insights. To this end, in this scoping review, we focus on synthesizing and analyzing the literature that uses AI techniques to fuse multimodal medical data for different clinical applications. More specifically, we focus on studies that only fused EHR with medical imaging data to develop various AI methods for clinical applications. We present a comprehensive analysis of the various fusion strategies, the diseases and clinical outcomes for which multimodal fusion was used, the ML algorithms used to perform multimodal fusion for each clinical application, and the available multimodal medical datasets. We followed the PRISMA-ScR guidelines. We searched Embase, PubMed, Scopus, and Google Scholar to retrieve relevant studies. We extracted data from 34 studies that fulfilled the inclusion criteria. In our analysis, a typical workflow was observed: feeding raw data, fusing different data modalities by applying conventional machine learning (ML) or deep learning (DL) algorithms, and finally, evaluating the multimodal fusion through clinical outcome predictions. Specifically, early fusion was the most used technique in most applications for multimodal learning (22 out of 34 studies). We found that multimodality fusion models outperformed traditional single-modality models for the same task. Disease diagnosis and prediction were the most common clinical outcomes (reported in 20 and 10 studies, respectively) from a clinical outcome perspective., Comment: Accepted in Nature Scientific Reports. 20 pages

Text detection in natural scene images has applications for autonomous driving, navigation help for elderly and blind people. However, the research on Urdu text detection is usually hindered by lack of data resources. We have developed a dataset of scene images with Urdu text. We present the use of machine learning methods to perform detection of Urdu text from the scene images. We extract text regions using channel enhanced Maximally Stable Extremal Region (MSER) method. First, we classify text and noise based on their geometric properties. Next, we use a support vector machine for early discarding of non-text regions. To further remove the non-text regions, we use histogram of oriented gradients (HoG) features obtained and train a second SVM classifier. This improves the overall performance on text region detection within the scene images. To support research on Urdu text, We aim to make the data freely available for research use. We also aim to highlight the challenges and the research gap for Urdu text detection., Comment: Accepted at NeurIPS ML4D workshop. arXiv admin note: text overlap with arXiv:2109.08060