Automatic segmentation of retinal images is an important task in computer-assisted medical image analysis for the diagnosis of diseases such as hypertension, diabetic and hypertensive retinopathy, and arteriosclerosis. Among the diseases, diabetic retinopathy, which is the leading cause of vision detachment, can be diagnosed early through the detection of retinal vessels. The manual detection of these retinal vessels is a time-consuming process that can be automated with the help of artificial intelligence with deep learning. The detection of vessels is difficult due to intensity variation and noise from non-ideal imaging. Although there are deep learning approaches for vessel segmentation, these methods require many trainable parameters, which increase the network complexity. To address these issues, this paper presents a dual-residual-stream-based vessel segmentation network (Vess-Net), which is not as deep as conventional semantic segmentation networks, but provides good segmentation with few trainable parameters and layers. The method takes advantage of artificial intelligence for semantic segmentation to aid the diagnosis of retinopathy. To evaluate the proposed Vess-Net method, experiments were conducted with three publicly available datasets for vessel segmentation: digital retinal images for vessel extraction (DRIVE), the Child Heart Health Study in England (CHASE-DB1), and structured analysis of retina (STARE). Experimental results show that Vess-Net achieved superior performance for all datasets with sensitivity (Se), specificity (Sp), area under the curve (AUC), and accuracy (Acc) of 80.22%, 98.1%, 98.2%, and 96.55% for DRVIE; 82.06%, 98.41%, 98.0%, and 97.26% for CHASE-DB1; and 85.26%, 97.91%, 98.83%, and 96.97% for STARE dataset.

Conventional nighttime face detection studies mostly use near-infrared (NIR) light cameras or thermal cameras, which are robust to environmental illumination variation and low illumination. However, for the NIR camera, it is difficult to adjust the intensity and angle of the additional NIR illuminator according to its distance from an object. As for the thermal camera, it is expensive to use as a surveillance camera. For these reasons, we propose a nighttime face detection method based on deep learning using a single visible-light camera. In a long-distance night image, it is difficult to detect faces directly from the entire image due to noise and image blur. Therefore, we propose Two-Step Faster region-based convolutional neural network (R-CNN) based on the image preprocessed by histogram equalization (HE). As a two-step scheme, our method sequentially performs the detectors of body and face areas, and locates the face inside a limited body area. By using our two-step method, the processing time by Faster R-CNN can be reduced while maintaining the accuracy of face detection by Faster R-CNN. Using a self-constructed database called Dongguk Nighttime Face Detection database (DNFD-DB1) and an open database of Fudan University, we proved that the proposed method performs better compared to other existing face detectors. In addition, the proposed Two-Step Faster R-CNN outperformed single Faster R-CNN and our method with HE showed higher accuracies than those without our preprocessing in nighttime face detection.

Recently, autonomous vehicles, particularly self-driving cars, have received significant attention owing to rapid advancements in sensor and computation technologies. In addition to traffic sign recognition, road lane detection is one of the most important factors used in lane departure warning systems and autonomous vehicles for maintaining the safety of semi-autonomous and fully autonomous systems. Unlike traffic signs, road lanes are easily damaged by both internal and external factors such as road quality, occlusion (traffic on the road), weather conditions, and illumination (shadows from objects such as cars, trees, and buildings). Obtaining clear road lane markings for recognition processing is a difficult challenge. Therefore, we propose a method to overcome various illumination problems, particularly severe shadows, by using fuzzy system and line segment detector algorithms to obtain better results for detecting road lanes by a visible light camera sensor. Experimental results from three open databases, Caltech dataset, Santiago Lanes dataset (SLD), and Road Marking dataset, showed that our method outperformed conventional lane detection methods.

Infertility is one of the most important health concerns worldwide. It is characterized by not being successful of pregnancy after some periods of periodic unprotected sexual intercourse. In vitro fertilization (IVF) is an assisted reproduction technique that efficiently addresses infertility. IVF replaces the actual mode of reproduction through a manual procedure wherein embryos are cultivated in a controlled laboratory environment until they reach the blastocyst stage. The standard IVF procedure includes the transfer of one or two blastocysts from several blastocysts that are grown in a controlled environment. The morphometric properties of blastocysts with their compartments such as trophectoderm (TE), zona pellucida (ZP), inner cell mass (ICM), and blastocoel (BL), are analyzed through manual microscopic analysis to predict viability. Deep learning has been extensively used for medical diagnosis and analysis and can be a powerful tool to automate the morphological analysis of human blastocysts. However, the existing approaches are inaccurate and require extensive preprocessing and expensive architectures. Thus, to cope with the automatic detection of blastocyst components, this study proposed a novel multiscale aggregation semantic segmentation network (MASS-Net) that combined four different scales via depth-wise concatenation. The extensive use of depthwise separable convolutions resulted in a decrease in the number of trainable parameters. Further, the innovative multiscale design provided rich spatial information of different resolutions, thereby achieving good segmentation performance without a very deep architecture. MASS-Net utilized 2.06 million trainable parameters and accurately detects TE, ZP, ICM, and BL without using preprocessing stages. Moreover, it can provide a separate binary mask for each blastocyst component simultaneously, and these masks provide the structure of each component for embryonic analysis. Further, the proposed MASS-Net was evaluated using publicly available human blastocyst (microscopic) imaging data. The experimental results revealed that it can effectively detect TE, ZP, ICM, and BL with mean Jaccard indices of 79.08, 84.69, 85.88%, and 89.28%, respectively, for embryological analysis, which was higher than those of the state-of-the-art methods.

Recently, real-time human age estimation based on facial images has been applied in various areas. Underneath this phenomenon lies an awareness that age estimation plays an important role in applying big data to target marketing for age groups, product demand surveys, consumer trend analysis, etc. However, in a real-world environment, various optical and motion blurring effects can occur. Such effects usually cause a problem in fully capturing facial features such as wrinkles, which are essential to age estimation, thereby degrading accuracy. Most of the previous studies on age estimation were conducted for input images almost free from blurring effect. To overcome this limitation, we propose the use of a deep ResNet-152 convolutional neural network for age estimation, which is robust to various optical and motion blurring effects of visible light camera sensors. We performed experiments with various optical and motion blurred images created from the park aging mind laboratory (PAL) and craniofacial longitudinal morphological face database (MORPH) databases, which are publicly available. According to the results, the proposed method exhibited better age estimation performance than the previous methods.