Current Issue : April-June Volume : 2026 Issue Number : 2 Articles : 5 Articles
In the domain of image and multimedia processing, image quality is a critical factor, as it directly influences the performance of subsequent tasks such as compression, transmission, and content analysis. Reliable assessment of image quality is therefore essential not only for benchmarking algorithms but also for ensuring user satisfaction in real-world multimedia applications. The most advanced Blind image quality assessment (BIQA) methods are typically built upon deep learning models and rely on complex architectures that, while effective, require substantial computational resources and large-scale training datasets. This complexity can limit their scalability and practical deployment, particularly in resourceconstrained environments. In this paper, we revisit a model inspired by one of the early applications of convolutional neural networks (CNNs) in BIQA and demonstrate that by leveraging recent advancements in machine learning—such as Bayesian hyperparameter optimization and widely used stochastic optimization methods (e.g., Adam)—it is possible to achieve competitive performance using a simpler, more scalable, and lightweight architecture. To evaluate the proposed approach, we conducted extensive experiments on widely used benchmark datasets, including TID2013 and KADID-10k. The results show that the proposed model achieves competitive performance while maintaining a substantially more efficient design. These findings suggest that lightweight CNN-based models, when combined with modern optimization strategies, can serve as a viable alternative to more elaborate frameworks, offering an improved balance between accuracy, efficiency, and scalability....
Edge detection plays a critical role in cutting-edge domains such as real-time monitoring and automatic driving, with optoelectronic device-based real-time image processing garnering significant attention. However, the poor endurance and unstable optical responsivity of conventional optoelectronic memristors constrain their application in highly integrated edge detection systems. In this study, a silicon-based integrated optoelectronic memristor based on SrTiO3:(Y2O3:ZrO2) (STO:YSZ) vertically aligned nanocomposite (VAN) structure is introduced, where the conductive channels at the spatial vertical interface providing an effective transport pathway. The device achieves excellent endurance (108 switching cycles) and stable multi-band (405–650 nm) optical switching. Additionally, it also exhibits the ability of simulating biological synaptic plasticity, implementing optical image extraction and ASCII code transmission. Importantly, edge detection of real-time road vehicle imagery is demonstrated via an optoelectronic memristor network. This work opens a promising paradigm for developing stable and high endurance machine vision systems based on optoelectronic memristor....
The curation of large-scale, diverse datasets for robust weed detection is extremely timeconsuming and resource-intensive in practice. Generative artificial intelligence (AI) opens up opportunities for image generation to supplement real-world image acquisition and annotation efforts. However, it is not a trial task to generate high-quality, multi-class weed images that capture the nuances and variations in visual representations for enhanced weed detection. This study presents a novel investigation of advanced stable diffusion (SD) integrated with a module with image prompt capability, IP-Adapter, for weed image generation. Using the IP-Adapter-based model, two image feature encoders, CLIP (contrastive language image pre-training) and BioCLIP (a vision foundation model for biological images), were utilized to generate weed instances, which were then inserted into existing weed images. Image generation and weed detection experiments are conducted on a 10-class weed dataset captured in vegetable fields. The perceptual quality of generated images is assessed in terms of Fréchet Inception Distance (FID) and Inception Score (IS). YOLOv11 (You Only Look Once version 11) models were trained for weed detection, achieving an improved mAP@50:95 of 1.26% on average when combining inserted weed instances with real ones in training, compared to using original images alone. Both the weed dataset and software programs in this study will be made publicly available. This study offers valuable perspectives into the use of IP-adapter-based SD for generating weed images and weed detection....
With the development of modern urban systems, the use of cameras for video surveillance of urban environments has become an essential requirement. However, in nighttime scenes, especially under foggy weather conditions, the visual quality can significantly degrade due to uneven atmospheric illumination, leading to color distortion and errors in transmission rate estimation. In this study, we propose a novel nighttime dehazing algorithm that integrates Retinex theory with the light–dark channel prior. Specifically, (1) we introduce a Retinex-based variational model to estimate global atmospheric light under low illumination conditions, effectively correcting color biases in the dehazed images; and (2) we combine the light and dark channel priors to refine the transmission rate estimation, resulting in an optimized dehazing framework. Extensive experiments on a real-world nighttime dataset demonstrate the method’s applicability to varying fog densities and complex light source distributions. Experimental results show significant improvements in both color fidelity and detail preservation, enhancing the reliability of urban infrastructure video surveillance systems in challenging nighttime foggy environments....
This work presents and validates an eye-tracking-based visual system for driving the delta robot. A delta robot is tracked by image processing based on vision servo control. The vision servo program is developed in C++ to perform image processing-based object detection. For image processing, Haar classifier-based methods are used. Finally, image processing and motion controller movements are integrated into one system to perform the visual servo-based motion of the end effector of the delta robot. Experiments are performed to validate the proposed method from the perspective of image processing. Moreover, this paper validates the kinematic analysis, which is vital for obtaining 3D information on the end-effector of the delta robot. The presented model can be implemented in eye clinics to facilitate ophthalmologists by replacing manual eye-checking equipment with automatic, unattended, computerized eye checkups....
Loading....