Browsing by Author "Huang, Chao-Hui"

Now showing 1 - 3 of 3

Bio-inspired computer fovea model based on hexagonal-type cellular neural network
(2007-01-01)
Huang, Chao-Hui
;
Lin, Chin-Teng
;
資訊工程學系
;
電控工程研究所
;
腦科學研究中心
For decades, numerous scientists have examined the following questions: "How do humans see the world?" and "How do humans experience vision?" To answer these questions, this study proposes a computer fovea model based on hexagonal-type cellular neural network (hCNN). Certain biological mechanisms of a retina can be simulated using an in-state-of-art architecture named CNN. Those biological mechanisms include the behaviors of the photoreceptors, horizontal cells, ganglions, and bipolar cells, and their co-operations in the retina. Through investigating the model and the abilities of the CNN, various properties of the human vision system can be simulated. The human visual system possesses numerous interesting properties, which provide natural methods of enhancing visual information. Various visual information enhancing algorithms can be developed using these properties and the proposed model. The proposed algorithms include color constancy, image sharpness, and some others. This study also discusses how the proposed model works for video enhancement and demonstrates it experimentally.
CNN-based hybrid-order texture segregation as early vision processing and its implementation on CNN-UM
(2007-10-01)
Lin, Chin-Teng
;
Huang, Chao-Hui
;
Chen, Shi-An
;
電控工程研究所
;
Institute of Electrical and Control Engineering
In this paper, a biologically inspired, CNN-based, multi-channel, texture boundary detection technique is presented. The proposed approach is similar to human vision system. The algorithm is simple and straightforward such that it can be implemented on the cellular neural networks (CNNs). CNN contains several important advantages, such as efficient real-time processing capability and feasible very large-scale integration (VLSI) implementation. The proposed algorithm also had been widely tested on synthetic texture images. Those texture images are randomly selected from the Brodatz textures database [1]. According to our simulation results, the boundaries of uniform textures can be detected quite successfully. For the nonuniform or nonregular textures, the results also indicate meaningful properties, and the properties also are consistent to the human visual sensation. The proposed algorithm also has been implemented on the CNN Universal Machine (CNN-UM), and yields similar results as the simulation on the PC. Based on the efficient performance of CNN-UM, the algorithm becomes very fast.
Image enhancement algorithm for hexagonal cellular neural networks
(2006)
Huang, Chao-Hui
;
Lin, Chin-Teng
;
電控工程研究所
;
Institute of Electrical and Control Engineering
In this paper, we propose an image enhancement algorithm for a display. Traditionally, high dynamic range algorithms handle the conversion from the scene in the real world to the screen in a display since the optical-physical conditions are changed. Similar reasons motivated our study of analyzing the relationship between the display and the Human Vision System (HVS). In this paper, we introduce an image enhancement algorithm, which is based on a well-known high-dynamic range compression algorithm, named Retinex theory. Retinex theory provides an approach of separating the illumination from the reflectance in a given image and thereby compensating for nonuniform lighting. The proposing algorithm is implemented on an advance Cellular Neural Network structure, the hexagonaltype Cellular Neural Network (hCNN). Via examining the stable central linear system of a hCNN, we are able to implement the Retinex theory and operate the CNN in the stable region. Meanwhile, we propose an approach to estimate the parameters in the Retinex theory based on the analysis of the interactions between the retina and the display. Those parameters vary depending on the environment and usually are difficult to obtain. Proposing algorithm is based on biological inspired technology. In our experiments, some quite good results are obtained.