In the field of computer vision, semantic segmentation became an important problem that has applications in fields such as autonomous driving and robotics. Image segmentation datasets, on the other hand, present substantial hurdles due to the high intra-class variability, which includes differences across car models or building designs, and the low inter-class variability, which makes it difficult to discern between objects such as buildings that have facades that are visually identical. A focus-enhanced ASPP module that is coupled with an upgraded backbone for semantic segmentation networks is presented in this study as a solution to the problems that have been identified. In order to augment the adaptability of extracted features, the proposed framework utilizes the capability of an attention ASPP module to implement attention processes within the multiscale module. In order to efficiently capture complex features, the encoder stage also makes use of a ResNet-50 backbone that has been properly optimized. In addition, to increase the robustness of the model, data augmentation approaches are applied. mDice of 87.82, mIoU of 79.05, and mean accuracy of 85.2 on the Stanford dataset, and mDice of 88.91, mIoU of 80.03, and mean accuracy of 89.84 on the Cityscapes dataset, according to experimental assessments, demonstrate that the developed technique performs at an accuracy level that is believed to be modern. As a result of these findings, the possibility for greatly improving semantic segmentation performance may be highlighted by integrating attention mechanisms, ASPP modules, and upgraded ResNet structures.

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.

Building segmentation is a difficult task due to the need for rich semantic features. Differences in the shape, color and size of buildings and their proximity to other features such as parking lots and streets make their recognition in high resolution images challenging. In this research, with the aim of extracting buildings from high-resolution images, deep Convolutional neural network architecture of the encoder-decoder type based on the modified DeepLabV3+ model has been used. In the Atrous module of this modified model, convolution layers are applied with lower rates compared to the original module, in order to achieve the goal of performing a more powerful semantic segmentation of small and large building objects. The performance of the proposed model in this research was evaluated using two data sets, WHU and INRIA, and the results showed that using lower Atrous rates and changing them to 4, 8, and 12 significantly improved the segmentation performance in both data sets. The proposed modified model was able to improve the IOU and F-Score indices compared with other advanced models in the WHU data set by 0. 39 and 0. 53, respectively. In addition, the modified method in the INRIA dataset improved both of the above indices by 0. 35. The proposed model in this research, based on the reduction of Atros rates to 4, 8 and 12 and the change in ResNet-50 layers, was able to achieve an IOU equal to 89. 51 in the WHU dataset and 76. 64 in the INRIA dataset in the extraction of construction charges.

This study explores the use of efficient deep learning algorithms for segmenting lower grade gliomas (LGG) in medical images. It evaluates various pre-trained Atrous-Convolutional architectures and U-Nets, proposing a novel transformer-based approach that surpasses traditional methods. DeepLabV3+ with MobileNetV3 backbone achieved the best results among pre-trained models, but the transformer-based approach excelled with superior segmentation accuracy and efficiency. Transfer learning significantly enhanced model performance on the LGG dataset, even with limited training samples, emphasizing the importance of selecting appropriate pre-trained models. The transformer-based method offers advantages such as efficient memory usage, better generalization, and the ability to process images of arbitrary sizes, making it suitable for clinical applications. These findings suggest that advanced deep learning techniques can improve diagnostic tools for LGG and potentially other cancers, highlighting the transformative impact of deep learning and transfer learning in medical image segmentation.

Object tracking through multiple cameras is a popular research topic in security and surveillance systems especially when human objects are the target. However, occlusion is one of the challenging problems for the tracking process. This paper proposes a multiple-camera-based cooperative tracking method to overcome the occlusion problem. The paper presents a new model for combining Convolutional neural networks (CNNs), which allows the proposed method to learn the features with high discriminative power and geometrical independence. In the training phase, the CNNs are first pre-trained in each of the camera views, and a Convolutional gating network (CGN) is simultaneously pre-trained to produce a weight for each CNN output. The CNNs are then transferred to the tracking task where the pre-trained parameters of the CNNs are re-trained by using the data from the tracking phase. The weights obtained from the CGN are used in order to fuse the features learnt by the CNNs and the resulting weighted combination of the features is employed to represent the objects. Finally, the particle filter is used in order to track objects. The experimental results showed the efficiency of the proposed method in this paper.

Speech recognition representing a communication between computers and human as a sub eld of computational linguistics or natural language processing has a long history. Automatic Speech Recognition (ASR), Text To Speech (TTS), speech to text, Continuous Speech Recognition (CSR), and interactive voice response systems are dierent approaches to solving problems in this area. The performance improvement is partially attributed to the ability of the Deep Neural Network (DNN) to model complex correlations in speech features. In this paper, unlike the use of conventional model for sequential data like voice that employs Recurrent Neural Networks (RNNs) with the emergence of dierent architectures in deep networks and good performance of Conventional Neural Networks (CNNs) in image processing and feature extraction, the application of CNNs was developed in other domains. It was shown that prosodic features for Persian language could be extracted via CNNs for segmentation and labeling speech for short texts. By using 128 and 200 lters for CNN and special architectures, 19. 46 error in detection rate and better time consumption than RNNs were obtained. In addition, CNN simplies the learning procedure. Experimental results show that CNN networks can be a good feature extractor for speech recognition in various languages.