- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
[IEEE 2018 IEEE International Conference on Imaging Systems and Techniques (IST) - Krakow, Poland (2018.10.16-2018.10.18)] 2018 IEEE International Conference on Imaging Systems and Techniques (IST) - Colour Constancy for Image of Non-Uniformly Lit Scenes
摘要： This paper presents a colour constancy algorithm for images of scenes lit by non-uniform light sources. The proposed method determines number of colour regions within the image using a histogram-based algorithm. It then applies the K-means++ algorithm on the input image, dividing the image into its segments. The proposed algorithm computes the normalized average absolute difference (NAAD) for each segment’s coefficients and uses it as a measure to determine if the segment’s coefficients have sufficient colour variations. The initial colour constancy adjustment factors for each segment with sufficient colour variation is calculated based on the principle that the average values of colour components of the image are achromatic. The colour constancy adjustment weighting factors (CCAWF) for each pixel of image are determined by fusing the CCAWFs of the segments’ with sufficient colour variations, weighted by their normalized Euclidian distance of the pixel from the center of the segments. Experimental results were generated using both indoor and outdoor benchmark images from the scene illuminated by single or multiple illuminants. Results show that the proposed method outperforms the state of the art techniques subjectively and objectively.
关键词： multi-illuminants,fusion,k-means segmentation,colour constancy
更新于2025-09-23 15:22:29
-
[IEEE 2018 International Conference on Platform Technology and Service (PlatCon) - Jeju (2018.1.29-2018.1.31)] 2018 International Conference on Platform Technology and Service (PlatCon) - Classification of Daytime and Night Based on Intensity and Chromaticity in RGB Color Image
摘要： Classification of daytime and night in the color image is a very important task in image processing based on color images acquired from CCTV. Also, weather classification must be performed before performing image processing such as weather report, shadow removal and fog detection. In this paper, we proposed the classification, whether a color image is daytime or night. We first set the range of pixels in the gray level image from 0 to 50, from 51 and over 101, and we estimated each range as daytime, evening and night. In the first step, it is estimated based on the intensity and chromaticity of the image. If the classification result based on the intensity and chromaticity image is the same, the process is terminated. Otherwise, the k-means segmentation is used in the second step to determine the final classification. Some experiments are conducted so as to verify the proposed method, and the classification is well performed. The execution time results up to the first step are about 0.31 seconds on average, and the execution up to the second step is changed according to the resolution of the image.
关键词： daytime and night,k-means segmentation,intensity,classification,chromaticity
更新于2025-09-19 17:15:36
-
[Advances in Intelligent Systems and Computing] Recent Findings in Intelligent Computing Techniques Volume 709 (Proceedings of the 5th ICACNI 2017, Volume 3) || Performance Analysis of Classifiers and Future Directions for Image Analysis Based Leaf Disease Detection
摘要： Plants play a very important role in the environment to maintain ecosystem, so this is our responsibility to protect it by detected disease which appears in it. In the plant disease, most symptoms appear on leaf, so by performing some image analysis we can detect these diseases very fast and accurately. This paper includes survey of different techniques which are used in leaf disease detection. To detect plant disease color conversion, Canny and Sobel edge detectors are used initially and then some segmentation techniques, i.e., Otsu and k-means, are used; after then, feature extraction takes place and is classified with classification techniques.
关键词： K-means segmentation,Edge detection,GLCM and classification technique
更新于2025-09-09 09:28:46