Personal identification based on vein pattern is one of the latest biometric approaches that have attracted lots of attention. Besides, Convolutional sparse Coding (CSC) is a popular model in the signal and image processing communities, resolving some limitations of the traditional patch-based sparse representations. As most existing CSC algorithms are suited for image restoration, we present a novel discriminative model based on CSC for dorsal hand vein recognition in this paper. The proposed method, discriminative local block coordinate descent (D-LoBCoD), is based on extending the LoBCoD algorithm by incorporating the classification error into the objective function that considers the performance of a linear classifier and the representational power of the filters simultaneously. Thus, for training, in each iteration, after updating the sparse coefficients and Convolutional filters, we minimize the classification error by updating the classifier’s parameters according to the label information. Finally, after training, the label of the query image will be determined by the trained classifier. One thousand two hundred dorsal hand vein images taken from 100 individuals are used to verify the validity of the proposed methods. The experimental results show that our method outperforms other competing methods. Further, we demonstrate that our proposed method is less dependent on the number of training samples because of capturing more representative information from the corresponding images.

Background and Objectives: High resolution multi-spectral (HRMS) images are essential for most of the practical remote sensing applications. Pan-sharpening is an effective mechanism to produce HRMS image by integrating the significant structural details of panchromatic (PAN) image and rich spectral features of multi-spectral (MS) images. Methods: The traditional pan-sharpening methods incur disadvantages like spectral distortion, spatial artifacts and lack of details preservation in the fused image. The pan-sharpening approach proposed in this paper is based on integrating wavelet decomposition and Convolutional sparse representation (CSR). The wavelet decomposition is performed on PAN and MS images to obtain low-frequency and high-frequency bands. The low-frequency bands are fused by exploring the CSR based activity level measurement. Results: The HRMS image is restored by implementing the inverse transform on fused bands. The fusion rules are constructed, thus to transfer the crucial details from source images to the fused image effectively. Conclusion: The proposed method produces HRMS images with rational spatial and spectral qualities. The visual outcomes and quantitative measures approve the eminence of the proposed fusion framework.

There are challenges such as depth perception and self-occlusion, in the field of 3D human pose estimation and reconstruction which obstructs precise estimation of body joints. In this paper, we first extract human pose by focusing on 2D ground-truth using sparse coding and. In the second approach, we use a learning-based Convolutional Neural Networks using sparse coding and a model based rectifier to extract the estimated pose. Pose estimation by proposedmethod has reduced the mean error of the reconstruction in comparison with the state of the artworks.

Background: The most common types of non-melanoma skin cancer are basal cell carcinoma (BCC), and squamous cell carcinoma (SCC). AKIEC-Actinic keratoses (Solar keratoses) and intraepithelial carcinoma (Bowen’ s disease)-are common noninvasive precursors of SCC, which may progress to invasive SCC, if left untreated. Due to the importance of early detection in cancer treatment, this study aimed to propose a computer-based model for identification non-melanoma malignancies. Methods: In this analytic study, 327 AKIEC, 513 BCC, and 840 benign keratosis images from human against machine with 10000 training dermoscopy images (HAM10000) were extracted. From each of these three types, 90% of the images were designated as the training set and the remaining images were considered as the test set. A deep learning Convolutional neural network (CNN) was developed for skin cancer detection by using AlexNet (Krizhevsky, et al., 2012) as a pretrained network. First, the model was trained on the training images to discriminate between benign and malignant lesions. In comparison with conventional methods, the main advantage of the proposed approach is that it does not need cumbersome and time-consuming procedures of lesion segmentation and feature extraction. This is because CNNs have the capability of learning useful features from the raw images. Once the system was trained, it was validated with test data to assess the performance. Study was carried out at Shahid Beheshti University of Medical Sciences, Tehran, Iran, in January and February, 2020. Results: The proposed deep learning network achieved an AUC (area under the ROC curve) of 0. 97. Using a confidence score threshold of 0. 5, a classification accuracy of 90% was attained in the classification of images into malignant and benign lesions. Moreover, a sensitivity of 94% and specificity of 86% were obtained. It should be noted that the user can change the threshold to adjust the model performance based on preference. For example, reducing the threshold increase sensitivity while decreasing specificity. Conclusion: The results highlight the efficacy of deep learning models in detecting non-melanoma skin cancer. This approach can be employed in computer-aided detection systems to assist dermatologists in identification of malignant lesions.

Introduction: Brain-Computer Interface (BCI) offers a non-muscle way between the human brain and the outside world to make a better life for disabled people. In BCI applications P300 signal has an effective role; therefore, distinguishing P300 and non-P300 components in EEG signal (i. e. P300 detection) becomes a vital problem in BCI applications. Recently, Convolutional Neural Networks (CNNs) have had a significant application in detection of P300 signals in the field of BCIs. The P300 signal has low Signal to Noise Ratio (SNR). On the other hand, the CNN detection rate is so sensitive to SNR; therefore, CNN detection rate drops dramatically when it is faces with P300 data. In this study, a novel structure is proposed to improve the performance of CNN in P300 signal detection by means of improving its performance against low SNR signals. Methods: In the proposed structure, sparse Representation-based Classification (SRC) was used as the first substructure. This block is responsible for prediction of the expected P300 signal among artifacts and noise. The second substructure performed P300 classification with Adadelta algorithm. Thanks to such SNR improvement scheme; the proposed structure is able to increase the rate of accuracy in the field of P300 signal detection. Results: To evaluate the performance of the proposed structure, we applied it on EPFL dataset for P300 detection, and then the achieved results were compared with those obtained from the basic CNN structure. The comparisons revealed the superiority of the proposed structure against its alternative, so that its True Positive Rate (TPR) was promoted about 19. 66%. Such improvements for false detections and accuracy parameters were 1. 93% and 10. 46%, respectively, which show the effectiveness of applying the proposed structure in detecting P300 signals. Conclusion: The better accuracy of the proposed algorithm compared to basic CNN, in parallel with its more robustness, showed that the sparse Representation-based Classification (SRC) had a considerable potential to be used as an improving idea in CNN-based P300 detection.

One of the challenges of Convolutional neural networks (CNNs), as the main tool of deep learning, is the large volume of some relevant models. CNNs, inspired form the brain, have millions of connections. Reducing the volume of these models is done by removing (pruning) the redundant connections of the model. Optimal Brain Damage (OBD) and sparse Regularization are among the famous methods in this field. In this study, a deep learning model has been trained and the effect of reducing connections with the aforementioned methods on its performance has been investigated. As the proposed approach, by combining the OBD and regularization methods its redundant connections were pruned. The resulting model is a smaller model, which has less memory and computational load than the original model, and at the same time its performance is not less than the original model. The experimental results show that the hybrid approach can be more efficient than each of the methods, in the most tested datasets. In one dataset , with the proposed method, the number of connections were reduced by 76%, without sacrificing the efficiency of the model. This reduction in model size has decreased the processing time by 66 percent. The smaller the software model, the more likely it is to be used on weaker hardware, found everywhere, and web applications.

The difficulties in the measurement of rainfall interception in forests confirm the necessity of presenting models. The widely used models for estimating rainfall interception are physical-based models, among which the sparse Gash is the most commonly used. We evaluated the sparse Gash model for estimating the rainfall interception of five forest stands (two chestnut-leaved oak stands, two oriental beech stands, and one velvet maple stand) in the Hyrcanian region. In each stand, the gross rainfall and throughfall were measured using 5 and 20 rainfall collectors, respectively, and rainfall interception was calculated by subtracting the throughfall from gross rainfall. To evaluate the performance of the model, we used statistical metrics: Error percentage (Error), Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and the Model Efficiency coefficient (CE). Based on the Pearson correlation coefficient, the correlation between the values estimated by the model and the observed values was statistically significant at a 95% confidence interval. In all forests, the values of the CE were higher than 0. 5, indicating the appropriate efficiency of the model. Based on the Error, the model showed good capability in estimating the rainfall interception of four forest stands (i. e., oriental beech in Lajim, chestnut-leaved oak in Kohmiyan and Sari, and velvet maple in Sari Error metric were found to be-10. 3%, +12. 7%, +10. 8%, and +15. 4%, respectively). Studying the performance of physically-based models in forests with different species and different allometric, climatic and rainfall characteristics completes the information gap about the efficiency of models to estimate rainfall interception.