Objective: Many common eye diseases and cardiovascular diseases can be diagnosed through retinal imaging. However, due to uneven illumination, image blurring, and low contrast, retinal images with poor quality are not useful for diagnosis, especially in automated image analyzing systems. Here, we propose a new image enhancement method to improve color retinal image luminosity and contrast. Methods: A luminance gain matrix, which is obtained by gamma correction of the value channel in the HSV (hue, saturation, and value) color space, is used to enhance the R, G, and B (red, green and blue) channels, respectively. Contrast is then enhanced in the luminosity channel of L ^* a ^* b ^* color space by CLAHE (contrast-limited adaptive histogram equalization). Image enhancement by the proposed method is compared to other methods by evaluating quality scores of the enhanced images. Results: The performance of the method is mainly validated on a dataset of 961 poor-quality retinal images. Quality assessment (range 0-1) of image enhancement of this poor dataset indicated that our method improved color retinal image quality from an average of 0.0404 (standard deviation 0.0291) up to an average of 0.4565 (standard deviation 0.1000). Conclusion: The proposed method is shown to achieve superior image enhancement compared to contrast enhancement in other color spaces or by other related methods, while simultaneously preserving image naturalness. Significance: This method of color retinal image enhancement may be employed to assist ophthalmologists in more efficient screening of retinal diseases and in development of improved automated image analysis for clinical diagnosis.

Existing obstacle avoidance systems do not consider the situation of hollowed-out obstacles. Therefore, in this paper, we design an assistive cane with visual odometry based on these requirements of the blind to aid them in attaining safe indoor navigation. The proposed device is portable, compact and adaptable. The assistive cane with visual odometry can be used not only to directly detect obstacles, but also to draw the attention of people around, providing multiple protection for the blind. In order to optimize the device parameters, we select the height of the camera and the speed of the voice broadcast as factors to design a complete factorial design, aiming to explore the parameter level that can make the passing time shortest and the success rate of obstacle avoidance highest. We invited two visually impaired people and two blindfolded students with normal vision as the experimental subjects. Each subject was required to conduct the experiments under nine combinations of device parameters. The subjects tried to avoid obstacles according to the voice prompts. The passing time and the success rate of obstacle avoidance were recorded. The experimental results show that the broadcast speed causes the significant effect to the success rate and both the two factors affect the passing time. In addition, we discuss the results of different subjects’ response surfaces and perceptual patterns and get the conclusion that different visual perceptual patterns, namely route representation and two different survey representations, have a certain impact on the setting of the optimal parameter level and the optimal passing time. The congenitally blind subject with route representation has the shortest optimal passing time in an unfamiliar environment, and the camera height should be set at the center of the hollowed-out obstacle, while the results are somewhat different for the acquired visual impairment subjects and the blindfolded normal vision subjects with survey representation. The camera height should be set between the center and the upper position of the obstacle. In summary, the camera height should be set at the center of the hollowed-out barrier and the broadcast speed should be set at the highest level. At the same time, the device parameters should be adjusted appropriately according to the visual perception pattern of users. Further researches are needed to analyze the perceptual patterns in depth.

Objective. The imaging photoplethysmography (IPPG) technique allows people to measure heart rate (HR) from face videos. However, motion artifacts caused by rigid head movements and nonrigid facial muscular movements are one of the key challenges. Approach. This paper proposes a self-adaptive region of interest (ROI) pre-tracking and signal selection method to resist motion artifacts. Based on robust facial landmark detection, we split the whole facial skin (including the forehead, cheeks, and chin) symmetrically into small circular regions. And two symmetric sub-regions constitute a complete ROI. These ROIs are tracked and the motion state is simultaneously assessed to automatically determine the visibility of these ROIs. The obscured or invisible sub-regions will be discarded while the corresponding symmetric sub-regions will be retained as available ROIs to ensure the continuity of the IPPG signal. In addition, based on the frequency spectrum features of IPPG signals extracted from different ROIs, a self-adaptive selection module is constructed to select the optimum IPPG signal for HR calculation. All these operations are updated per frame dynamically for the real-time monitor. Results. Experimental results on the four public databases show that the IPPG signal derived by our proposed method exhibits higher quality for more accurate HR estimation. Compared with the previous method, metrics of the evaluated HR value on our approach demonstrates superior or comparable performance on PURE, VIPL-HR, UBFC-RPPG and MAHNOB-HCI datasets. For instance, the RMSEs on PURE, VIPL-HR, and UBFC-RPPG datasets decrease from 4.29, 7.62, and 3.80 to 4.15, 3.87, and 3.35, respectively. Significance. Our proposed method can help enhance the robustness of IPPG in real applications, especially given motion disturbances.

Ultra-high field magnetic resonance imaging (MRI), such as 7-Tesla (7T) MRI, provides significantly enhanced tissue contrast and anatomical details compared to 3T MRI. However, 7T MRI scanners are more costly and less accessible in clinical settings than 3T scanners. In this paper, we propose a wavelet-based frequency attention network (WFANet) and a semi-supervised method named dual domain consistency learning (DDCL), and combine them to form a WFANet-DDCL framework for 7T MRI synthesis. WFANet leverages the frequency sensitivity of the proposed wavelet-based frequency attention encoder (WFAE) along with the large receptive field of dilated convolution. WFAE is proposed as an independent module to capture multi-scale frequency attention via the proposed wavelet-based frequency attention (WFA) mechanism. WFAE can be integrated into any backbone network as a plug-and-play component and improve network performance. To tackle the challenge of limited paired data for network training, DDCL is proposed to take advantage of both paired and unpaired data. Frequency domain perturbation is proposed and combined with Gaussian noise to regularize the supervised learning process in dual domains, better avoiding overfitting. Extensive experimental results demonstrate that WFANet-DDCL can achieve comparable performance to state-of-the-art supervised methods even using 66% of all paired data.