Search

One of the vital characteristics that determine the health condition of a person is the shape and number of the red blood cells, white blood cells and platelets present in one's blood. Any abnormality in these characteristics is an indication of the person suffering from diseases like anaemia, leukaemia or thrombocytosis. The counting of the blood cell is conventionally made by means of microscopic studies with the application of suitable chemical substances in the blood. The conventional methods pose challenges in the analysis in terms of manual labour and are time-consuming and costly tasks requiring highly skilled medical professionals. This paper proposes a novel scheme to analyse the blood sample of an individual by employing a visual question answering (VQA) system, which accepts a blood smear image as input and answers questions pertaining to the sample, viz. amount of blood cells, nature of abnormalities, etc. very quickly without requiring the service of a skilled medical professional. In VQA, the computer generates textual answers to questions about an input image. Solving this difficult problem requires visual understanding, question comprehension and deductive reasoning. The proposed approach exploits a convolutional neural network for question categorisation and an object detector with an attention mechanism for visual comprehension. The experiment has been conducted with two types of attention: (1) convolutional block attention module and (2) squeeze-and-excitation network which facilitates very fast and reliable results. A VQA dataset has been created for this study due to the unavailability of a public dataset, and the proposed system exhibited an accuracy of 94% for numeric response questions/yes or no type questions and has a BLEU score of 0.91. It is also observed that the attention-based object recognition model of the proposed system for counting the blood characteristics has an accuracy of 97%, 100% and 98% for red blood cell count, white blood cell count and platelet count, respectively, which is an improvement of 1%, 0.06% and 1.61% as compared to the state-of-the-art model. [ABSTRACT FROM AUTHOR]

Visual question answering (VQA) research has garnered increasing attention in recent years. It is considered a visual Turing test because it requires a computer to respond to textual questions based on an image. Expertise in computer vision, natural language processing, knowledge understanding, and reasoning is required to solve the problem of VQA. Most techniques employed for VQA consist of models that are developed to learn the combination of image and question features along with the expected answer. The techniques chosen for image and question feature extraction and combining the features change with each model. This method of teaching a model of the question–answer pattern is ineffective for queries that involve counting and reasoning. This approach also requires considerable resources and large datasets for the training. The general VQA datasets feature a restricted number of items as responses to counting questions (< 1 0), and the distribution of the answers is not uniform. To investigate these issues in VQA, we created synthetic datasets that could be modified to adjust the number of objects in the image and the amount of occlusion. Specifically, a zero-shot learning VQA system was devised for counting-related questions that provide answers by analyzing the output of an object detector and the query keywords. Using synthetic datasets, our model generated 100% correct results. Testing on the benchmark datasets task directed image understanding challenge (TDIUC) and TallyQA-simple indicated that the proposed model matched the performance of the learning-based baseline models. This methodology can be used efficiently for counting VQA questions confined to certain domains when the number of items to be counted is significant. [ABSTRACT FROM AUTHOR]

The article titled "Denoising transthoracic echocardiographic images in regional wall motion abnormality using deep learning techniques" has been retracted by the publisher due to concerns about compromised editorial handling, peer review process, and inappropriate references. Authors A. Shamla Beevi, S. Ratheesha, and Saidalavi Kalady have not responded to correspondence regarding the retraction, and the publisher has been unable to contact author Jinu James Chakol. The retracted article is available as supplementary information online. [Extracted from the article]

Visual effects such as shadows and highlights appear in photographs due to variations in lighting conditions. Although these effects add more meaning to the images, they pose various problems to specific computer vision algorithms. Hence, the removal of shadows and highlights is often considered as a prerequisite to such algorithms. This paper presents an interactive technique for shadow elimination from images. Our method requires user input in the form of rough strokes on the shadow region and its corresponding non-shadow region in the image. We further use quaternion rotation in the YCbCr color space to derive an image that is invariant to shadows. The actual colors of the image are finally recovered by color transfer from the original shadow image. The proposed method takes less time to generate the shadow-free image and does not necessitate the detection of shadows prior to its removal. Also, unlike the existing shadow-removal techniques, our method generates invariant image with minor texture loss. Experimental findings are reported to demonstrate the performance of our shadow-removal technique. [ABSTRACT FROM AUTHOR]

Enhancing Synthetic Aperture Radar (SAR) images for sharp and detailed images through super-resolution (SR) is of great significance in many remote sensing applications. Due to the inherent resolution limitations and the cost incurred for further development of sensor devices, image enhancements through image processing techniques have become more popular. However, in these techniques, the soft edges present in the images are not reconstructed completely, thereby marring the clarity of the generated image. This paper presents a method to restore more details in the image by adaptively adjusting the measurement noise covariance and process noise covariance into the intensity estimation framework for SAR image super-resolution. For this, an Adaptive Importance Sampling Unscented Kalman Filter (ISUKF) framework is implemented using the covariance matching technique. Experimental results indicate that the super-resolution using ISUKF framework performs better, regarding denoising and feature preservation, when accounted for the measurement and process noise covariance. It also outperforms the other recent and standard SR techniques covered in the literature. • An improvement for the existing ISUKF based SAR image super resolution is proposed. • Fixed filter design replaced to adapt the dynamics in the environment. • Significant improvement in denoising and feature preservation. • Superior ability to reconstruct soft edges in the SAR image. [ABSTRACT FROM AUTHOR]

Network-on-Chip (NoC) has become a cost-effective communication interconnect for Tiled Chip Multicore Processor systems. The communication between cores is done through packet exchange. As the computational intensity of applications increases, the amount of packet exchange between cores will also increase. The improper routing of these packets will result in high congestion thereby degrading the system performance. This marks the need for congestion-aware routing in NoC. In the real world, the applications running in NoC create diverse traffic, which in turn creates challenges in routing. Such challenges have resulted in more researchers relying on machine learning algorithms to tackle them. However, the issues pertaining to storage overhead and packet latency prevail in such methodologies. This paper presents an adaptive routing algorithm DeepNR, which uses a deep reinforcement learning approach. The proposed approach considers network information for state representation, routing directions for actions, and queuing delay for reward function. Experiments carried out on synthetic as well as real-time traffics to demonstrate the effectiveness and efficiency of DeepNR using the Gem5 simulator. The results obtained for DeepNR indicate a reduction of up to 21.25% and 44% in overall packet latency under high traffic conditions on real and synthetic traffic respectively, as compared to the existing approaches. Also, DeepNR achieves a throughput of above 90% in both the traffic scenarios. [ABSTRACT FROM AUTHOR]