Search

Today, the digital photos especially identity images are used in almost every form filling application. As user is uploading his/her photographs, the image quality issues will come up. Especially, if some automatic processing like face recognition is happening at back end. The image quality parameters include resolution/dimensions, size and blur. Apart form blur, rest can be checked by simple conditions. But, blur detection cannot be solved in a trivial way. Here we are proposing a deep learning based approach for detecting the blur in an image. We have prepared data comprising 250,000 identity images. Our aim is to provide a comprehensive list of clear and blur images before learning happens. Apart from naturally blurred images, we have added five types of artificial blur into the images for better generalization. We have done comparative analysis of our approach to statistical feature extractor i.e. BRISQUE which was trained on SVM. We have empirically selected the convolutional network with 4 layers. Performance evaluation shows the proposed approach is giving 98.05% on 113,000 images, and thus outperforming BRISQUE using SVM.

In this paper, we evaluated the recognition performance of CRNN (Convolutional Recurrent Neural Network) on Indian language printed documents. We compared the current CRNN performance with MDLSTM (2 dimensional LSTM) and Tesseract (LSTM) on same test bed. The CRNN outperformed the previous approaches. Several experiments are done on 7 Indian languages i.e. Hindi, Marathi, Tamil, Kannada, Malayalam, Bangla and Gurumukhi. This CRNN architecture is feed with pre-segmented lines. Dataset used contained approximately 5000 pages for each language which were then divided into training, validation and testing set. The proposed fused network i.e. CRNN, does the task of feature extraction and sequence labeling as a single unit. Wherein, Convolutional Neural Network (CNN) is pitched in especially to eliminate dependency of hand crafted features. It directly processes 2D image (binarized) of each line and extracts features based on the learning kernels. Then, Recurrent Neural Network (RNN) with BLSTM (bi directional LSTM) architecture is applied on learned features to produce inference/ sequence probabilities. The output of CTC layer transcripts these probabilities into Unicode range of the evaluated language and one blank label. These layers and their parameters are empirically selected and kept same for all the languages.

In this paper, we evaluated the recognition performance of BLSTM (Bidirectional LSTM) and MDLSTM (two-dimensional LSTM) neural network architecture on printed documents. We also compare the performance of 2 architectures with tesseract on same test bed. We demonstrate our experimentation on 7 Indian languages i.e. Hindi, Marathi, Tamil, Kannada, Malayalam, Bangla and Gurumukhi. The input to both the architecture will be segmented lines. The data-set used contains approximate 5000 pages for each language which then divided into train, validation and test set. The Histogram of Gradients are extracted at line level to feed into the BLSTM network. Whereas MDLSTM processes 2D image (raw pixels) of each line. The level and number of hidden layers in both the architectures are empirically selected and kept same for all the languages. The output CTC layer will contain the number of unicode present in the evaluated languages and one blank label. The input layer was fully connected to hidden layers, and these were fully connected to themselves and to the output layer. The validated result shows MDLSTM outperforms both BLSTM and tesseract for all the languages included in our experimentation.

RF inductors design and their optimization for inductance and quality factor is key factor for RF Circuits and ICs. Spiral shaped RF inductors are proposed and followed by the enhancing performance of inductor using variation in structures. In this paper, we have proposed an inductor design which can have optimized inductance as well as quality factor and which operate at multi frequency range (up to 200 GHz). This will improve the RF range over which we can use these improved inductance and Q factor in tuned amplifiers and voltage control oscillators.

In this research, a new technique For Content Based Image Retrieval (CBIR) with contrast enhancement using multi-feature and multi kernel Support Vector Machine (SVM) method. Color moment (CM), Auto Correlogram (AC), Discrete Wavelet Transform (DWT), Gabor Filter (GF) features are proposed. We extended the previous work which used binary SVM classifier and color features. First of all take a query image, then the appearance of the image is improved using contrast adjustment. For its color feature, apply color moment method, convert RGB into HSVcolor space and make feature vector (mean). Extract texture features using GF, DWT and inverse difference moment (IDM). Skewness and Kurtosis are extracted for shape feature. Variance, root mean square (RMS) is extracted for color feature. After extracting the image feature, we used a supervised learning technique which is known as Multi kernel SVM to determine the optimal outcomes. After combining the features and classify the data. And finally compare the results with the previous method. The proposed method gives better accuracy and precision value. This work is simulated on MATLAB2012 simulator.

Vehicular ad-hoc network is growing area of research because of it's infrastructure and highly moving scenario. This network provide intelligence transporation system for users so that movement is going to be easy. In this paper we study about Vehicular network and it's application. In our proposed work we apply clustering approach on the basis of density and moveability, neighbor selection happen on the basis of distance for secure transmission we apply AES technique for encryption and decryption, novelity of our propose work we provide by results.

The most common cancer of endocrine gland is thyroid cancer. TSH binds with TSHR and activates different signaling pathways. MAPK is the most occurring pathways, it potentially activates the TG gene expression. p53, Wnt and Apoptosis increase the TG gene expression and injury in thyroid gland. Commonly occurring form of thyroid cancer is papillary thyroid carcinoma (PTC). This study predicts several therapeutic targets in different pathways. In this paper four molecular interaction map viz MAPK, p53, Wnt and Apoptosis pathways were taken for study which probably regulates uncontrolled cell division and thyroid hormone synthesis pathways.

We present a document binarization scheme that is intended at consistently binarizing a range of degraded color document images. The proposed solution makes use of a mean-shift algorithm based segmentation applied at different scales of the image and a contrast enhanced version of the popular Niblack's thresholding method. The solution has been evaluated using standard metrics used in a prominent binarization competition and has also been subject to an end-to-end evaluation by use in an OCR system. The proposed solution was found to perform at par or better than existing state of the art binarization solutions and was found to always be more consistent in performance than the state of the art.