Over the years, the number of vehicular traffic on the road has dramatically increased, causing the rate of road accidents also to increase. As a result, research on vehicle development and safety has significantly grown. One of the essential systems in autonomous vehicles for ensuring a secure circumstance for drivers and passengers is the Advanced Driver Assistance System (ADAS). Adaptive Cruise Control, Automatic Braking/Steer Away, Lane-Keeping System, Blind Spot Assist, Lane Departure Warning System, and Lane Detection are examples of ADAS. Lane detection displays information specific to the geometrical features of lane line structures to the vehicle’s intelligent system to show the position of lane markings. This article reviews the methods employed for lane detection in an autonomous vehicle. A systematic literature review (SLR) has been carried out to analyze the most delicate approach to detecting the road lane for the benefit of the automation industry. One hundred and two publications from well-known databases were chosen for this review. The trend was discovered after thoroughly examining the selected articles on the method implemented for detecting the road lane from 2018 until 2021. The selected literature used various methods, with the input dataset being one of two types: self-collected or acquired from an online public dataset. In the meantime, the methodologies include geometric modeling and traditional methods, while AI includes deep learning and machine learning. The use of deep learning has been increasingly researched throughout the last four years. Some studies used stand-alone deep learning implementations for lane detection problems. Meanwhile, some research focuses on merging deep learning with other machine learning techniques and classical methodologies. Recent advancements imply that attention-mechanism has become a popular combined strategy with deep learning methods. The use of deep algorithms in conjunction with other techniques showed promising outcomes. This research aims to provide a complete overview of the literature on lane detection methods, highlighting which approaches are currently being researched and the performance of existing state-of-the-art techniques. This review yields a valuable foundation on lane detection techniques, challenges, and opportunities and supports new research works in this automation field. For further study, it is suggested to put more effort into accuracy improvement, increased speed performance, and more challenging works on various extreme conditions in detecting the road lane.

Algae represent the majority of the diversity on Earth and are a large group of organisms that have photosynthetic properties that are important to life. The species of algae are estimated to be more than 1 million, they play an important role in many fields such as agriculture, industry, food, medicine. It is important to determine the type of algae to determine if it is harmful or useful, and to indicate the health of the ecosystem, water quality, health, and safety risks. The conventional process of classifying algae is difficult, tedious, and time-consuming. Recently various computer vision techniques have been used to classify algae to overcome challenges and automate the process of classification. This paper presents a review of research done on image classification for microorganism algae using machine learning and deep learning techniques. The paper focuses on three important research questions to highlight the challenges of classifying microalgae. A systematic literature review or SLR has been conducted to determine how deep learning and machine learning have improved and enhanced automatic microalgae classification rather than manual classification. 51 articles have been included from well-known databases. The outcome of this SLR is beneficial due to the detailed analysis and comprehensive overview of the algorithms and the architectures and information about the dataset used in each included article. The future work focuses on getting a large dataset with high resolution, trying different methods to manage imbalance problems, giving more attention to the fusion of deep learning techniques and traditional machine learning techniques.

Enhancement of captured hand vein images is essential for a number of purposes, such as accurate biometric identification and ease of medical intravenous access. This paper presents an improved hand vein image enhancement technique based on weighted average fusion of contrast limited adaptive histogram equalization (CLAHE) and fuzzy adaptive gamma (FAG). The proposed technique is applied using three stages. Firstly, grey level intensities with CLAHE are locally applied to image pixels for contrast enhancement. Secondly, the grey level intensities are then globally transformed into membership planes and modified with FAG operator for the same purposes. Finally, the resultant images from CLAHE and FAG are fused using improved weighted averaging methods for clearer vein patterns. Then, matched filter with first-order derivative Gaussian (MF-FODG) is employed to segment vein patterns. The proposed technique was tested on self-acquired dorsal hand vein images as well as images from the SUAS databases. The performance of the proposed technique is compared with various other image enhancement techniques based on mean square error (MSE), peak signal-to-noise ratio (PSNR), and structural similarity index measurement (SSIM). The proposed enhancement technique’s impact on the segmentation process has also been evaluated using sensitivity, accuracy, and dice coefficient. The experimental results show that the proposed enhancement technique can significantly enhance the hand vein patterns and improve the detection of dorsal hand veins.

Silicon wafer defect classification is crucial in improving fabrication and chip production. While deep learning methods have been successful in single-defect wafer classification, the increasing complexity of the fabrication process has introduced the challenge of multiple defects on wafers, which requires more robust feature learning and classification techniques. Attention mechanisms have been used to enhance feature learning for multiple wafer defects. However, they have limited use in a few mixed-type defect categories, and their performance declines as the number of mixed patterns increases. This work proposes an attention-augmented convolutional neural networks (A2CNN) model for enhanced discriminative feature learning of complex defects. The A2CNN model emphasizes the features in the channel and spatial dimensions. Additionally, the model adopts the focal loss function to reduce misclassification and a global average pooling layer to enhance the network’s generalization by reducing overfitting. The A2CNN model is evaluated on the MixedWM38 wafer defect dataset using 10-fold cross-validation. It achieves impressive results, with accuracy, precision, recall, and F1-score reported as 98.66%, 99.0%, 98.55%, and 98.82% respectively. Compared to existing works, the A2CNN model performs better by effectively learning valuable information for complex mixed-type wafer defects.

Deep learning is notably successful in data analysis, computer vision, and human control. Nevertheless, this approach has inevitably allowed the development of DeepFake video sequences and images that could be altered so that the changes are not easily or explicitly detectable. Such alterations have been recently used to spread false news or disinformation. This study aims to identify Deepfaked videos and images and alert viewers to the possible falsity of the information. The current work presented a novel means of revealing fake face videos by cascading the convolution network with recurrent neural networks and fully connected network (FCN) models. The system detection approach utilizes the eye-blinking state in temporal video frames. Notwithstanding, it is deemed challenging to precisely depict (i) artificiality in fake videos and (ii) spatial information within the individual frame through this physiological signal. Spatial features were extracted using the VGG16 network and trained with the ImageNet dataset. The temporal features were then extracted in every 20 sequences through the LSTM network. On another note, the pre-processed eye-blinking state served as a probability to generate a novel BPD dataset. This newly-acquired dataset was fed to three models for training purposes with each entailing four, three, and six hidden layers, respectively. Every model constitutes a unique architecture and specific dropout value. Resultantly, the model optimally and accurately identified tampered videos within the dataset. The study model was assessed using the current BPD dataset based on one of the most complex datasets (FaceForensic++) with 90.8% accuracy. Such precision was successfully maintained in datasets that were not used in the training process. The training process was also accelerated by lowering the computation prerequisites.