scispace - formally typeset
Search or ask a question
Journal Article

Image Segmentation Algorithm Study for Low Contrast Image

TL;DR: The algorithm of image segmentation is analyzed and the method based on space region variance and gray region variance is proposed for image enhancement and gray segmentation, which shows it is valid for low contrast image.
Abstract: The algorithm of image segmentation is analyzed The property of low contrast and gray randomly distributed image is considered and the method based on space region variance and gray region variance is proposed for image enhancement and gray segmentation The experimental results show this method is valid for low contrast image
Citations
More filters
Journal ArticleDOI
TL;DR: A combination of selfadaptive gray equilibrium and vertical projection is proposed that can extract the low contrast single line, prove the effectiveness of the algorithm through the comparative experiments, and improve the angle measurement accuracy to ±1′′, repeatability superior to 1×10 , and algorithm stability is good.
Abstract: High precision refractivity of optical glass is an important condition to ensure the image quality, mainly by the V-prism refractometer detection. In V-prism refractometer in using image alignment, the image quality of single line in the collimator directly affects the alignment accuracy in measurement, especially as the contrast between single line and background is low, affects the accuracy in measurement. A combination of selfadaptive gray equilibrium and vertical projection is proposed. This method can extract the low contrast single line, prove the effectiveness of the algorithm through the comparative experiments, and improve the angle measurement accuracy to ±1′′ , repeatability superior to 1×10 , and algorithm stability is good. It has important practical significance to achieve high precision measurement of optical glass refractive index.

2 citations

Book ChapterDOI
23 Aug 2019
TL;DR: A novel approach for unsupervised object segmentation, termed as saliency guided intersecting cortical model (SG-ICM), is proposed in this paper, and results reveal that this model has great potential in aerial reconnaissance application.
Abstract: Unsupervised object segmentation aims to assign same label to pixels of object region with feature homogeneity, which can be applied to object detection and recognition. Intersecting cortical model (ICM) can simulate human visual system (HVS) to process image for many applications, and at the same time, saliency detection can also simulate HVS to locate the most important object in a scene. Based on saliency detection, a novel approach for unsupervised object segmentation, termed as saliency guided intersecting cortical model (SG-ICM), is proposed in this paper. Instead of using gray-scale and spatial information to motivate ICM neurons traditionally, it is better to exploit saliency characteristic to guide ICM. In this paper, we plan to do saliency detection exploiting an improved dynamic guided filtering to analyze significance of different regions in same scene. The proposed saliency feature lies on: (1) the proposed saliency detection is based on region instead of pixel; (2) the dynamic guided filter is designed to accelerate the filtering; (3) in order to improve SG-ICM for object segmentation, at the each iteration, we use adaptive and simple threshold, which can raise the speed of this model. We check the proposed algorithm on common database of DOTI, color image from public database of MSRA with ground truth annotation. Experimental results show that the proposed method is superior to the others in terms of robustness of object segmentation, furthermore, it does not need any training. In addition, this method is effective for aerial image, the detection results reveal that this model has great potential in aerial reconnaissance application.

1 citations