• Journal of Sensor Science and Technology
• /
• v.13 no.3
• /
• pp.188-194
• /
• 2004

With a remarkable advance in CMOS (complimentary metal-oxide-semiconductor) process technology, a variety of vision sensors with signal processing circuits for complicated functions are actively being developed. Especially, as the principles of signal processing in human retina have been revealed, a series of vision chips imitating human retina have been reported. Human retina is able to detect the edge and motion of an object effectively. The edge detection among the several functions of the retina is accomplished by the cells called photoreceptor, horizontal cell and bipolar cell. We designed a CMOS vision chip by modeling cells of the retina as hardwares involved in edge and motion detection. The designed vision chip was fabricated using $0.6{\mu}m$ CMOS process and the characteristics were measured. Having reliable output characteristics, this chip can be used at the input stage for many applications, like targe tracking system, fingerprint recognition system, human-friendly robot system and etc.

• International Journal of Internet, Broadcasting and Communication
• /
• v.14 no.2
• /
• pp.136-146
• /
• 2022

Some surface defects make the weak quality of steel materials. To limit these defects, we advocate a one-stage detector model RetinaNet among diverse detection algorithms in deep learning. There are several backbones in the RetinaNet model. We acknowledged two backbones, which are ResNet50 and VGG19. To validate our model, we compared and analyzed several traditional models, one-stage models like YOLO and SSD models and two-stage models like Faster-RCNN, EDDN, and Xception models, with simulations based on steel individual classes. We also performed the correlation of the time factor between one-stage and two-stage models. Comparative analysis shows that the proposed model achieves excellent results on the dataset of the Northeastern University surface defect detection dataset. We would like to work on different backbones to check the efficiency of the model for real world, increasing the datasets through augmentation and focus on improving our limitation.

• Journal of Multimedia Information System
• /
• v.5 no.2
• /
• pp.79-82
• /
• 2018

Due to the handheld holding of smartphones and the presence of light leakage and non-balanced contrast, the detection of the retina area in smartphone-captured fundus images is more challenging than retinography-captured fundus images. This paper presents a computationally efficient image processing pipeline in order to detect and enhance the retina area in smartphone-captured fundus images. The developed pipeline consists of five image processing components, namely point spread function parameter estimation, deconvolution, contrast balancing, circular Hough transform, and retina area extraction. The results obtained indicate a typical fundus image captured by a smartphone through a D-EYE lens is processed in 1 second.

• Journal of the Semiconductor & Display Technology
• /
• v.19 no.2
• /
• pp.11-15
• /
• 2020

In a typical initial setup of a PCB component inspection system, operators should manually input various information such as category, position, and inspection area for each component to be inspected, thus causing much inconvenience and longer setup time. Although there are many deep learning based object detectors, RetinaNet is regarded as one of best object detectors currently available. In this paper, a method using an extended RetinaNet is proposed that automatically detects its component category and position for each component mounted on PCBs from a high-resolution color input image. We extended the basic RetinaNet feature pyramid network by adding a feature pyramid layer having higher spatial resolution to the basic feature pyramid. It was demonstrated by experiments that the extended RetinaNet can detect successfully very small components that could be missed by the basic RetinaNet. Using the proposed method could enable automatic generation of inspection areas, thus considerably reducing the setup time of PCB component inspection systems.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.39 no.6
• /
• pp.49-58
• /
• 2002

Based on electrophysiological retina mechanism, a retina model is proposed, which has similar response characteristics compared with the real primate retina. Photoreceptors, horizontal cells, and bipolar cells are modeled based on the previously studied retina models. And amacrine cells known to have relation to movements detection, and bipolar cell terminals are newly modeled using 3 NDP mechanism. The proposed model verified by analyzing the spatial response characteristics to stationary and moving stimuli, and characteristics for different speeds. Through this retina model, human vision system could be applied to computer vision systems for movement detection, and it could be the basic research for the implantable artificial retina.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.4
• /
• pp.519-525
• /
• 2022

The face detection task of detecting a person's face in an image is used as a preprocess or core process in various image processing-based applications. The neural network models, which have recently been performing well with the development of deep learning, are dependent on 2D images, so if noise occurs in the image, such as poor camera quality or pool focus of the face, the face may not be detected properly. In this paper, we propose a face detection method that uses depth information together to reduce the dependence of 2D images. The proposed model was trained after generating and preprocessing depth information in advance using face detection dataset, and as a result, it was confirmed that the FRN model was 89.16%, which was about 1.2% better than the RetinaNet model, which showed 87.95%.

• Journal of Multimedia Information System
• /
• v.8 no.2
• /
• pp.79-84
• /
• 2021

Detecting brain tumors of different sizes is a challenging task. This study aimed to identify brain tumors using detection algorithms. Most studies in this area use segmentation; however, we utilized detection owing to its advantages. Data were obtained from 64 patients and 11,200 MR images. The deep learning model used was RetinaNet, which is based on ResNet152. The model learned three different types of pre-processing images: normal, general histogram equalization, and contrast-limited adaptive histogram equalization (CLAHE). The three types of images were compared to determine the pre-processing technique that exhibits the best performance in the deep learning algorithms. During pre-processing, we converted the MR images from DICOM to JPG format. Additionally, we regulated the window level and width. The model compared the pre-processed images to determine which images showed adequate performance; CLAHE showed the best performance, with a sensitivity of 81.79%. The RetinaNet model for detecting brain tumors through deep learning algorithms demonstrated satisfactory performance in finding lesions. In future, we plan to develop a new model for improving the detection performance using well-processed data. This study lays the groundwork for future detection technologies that can help doctors find lesions more easily in clinical tasks.

• Journal of Sensor Science and Technology
• /
• v.10 no.2
• /
• pp.91-100
• /
• 2001

A $8{\times}8$ foveated (log-polar) retina chip for edge detection has been designed and fabricated using CMOS technology. Retina chip performs photo-input sensing, edge extraction and motion detection and we focused edge extraction. The pixel distribution follows the log-polar transform having more resolution in the center than in the periphery and can reduce image information selectively. This kind of structure has been already employed in simple image sensors for normal cameras, but never in edge detection retina chip. A scaling mechanism is needed due to the different pixel size from circumference to circumference. A mechanism for current scaling in this research is channel width scaling of MOS transistor. The designed chip has been fabricated using standard $1.5{\mu}m$ single-poly double-metal CMOS technology.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.9 no.7
• /
• pp.1594-1600
• /
• 2005

Recently many researches have been studied in the human vision model to solve the Wblem of the machine vision. Starting from research on the human visual system, first, we investigate the mechanisms of retina through physiological and biological evidence. In retina, input data was processed information processing that was data reduction edge detection, and emphasizing region. The processed image was recognized by region. In this paper, we proposed retinal algorithms that process data reduction and edge detection by the wavelet transform and emphasize region contrast. In experiments, the proposed model simulates processing the retina outputs in the levels and compares with outputs.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.5
• /
• pp.737-745
• /
• 2023

This paper discusses a study on developing an artificial intelligence model to detect incidents of fires in distribution switchboard using thermal images. The objective of the research is to preprocess collected thermal images into suitable data for object detection models and design a model capable of determining the occurrence of fires within distribution panels. The study utilizes thermal image data from AI-HUB's industrial complex for training. Two CNN-based deep learning object detection algorithms, namely Faster R-CNN and RetinaNet, are employed to construct models. The paper compares and analyzes these two models, ultimately proposing the optimal model for the task.