Extracting vein skeleton with little distortion from the vein image is very important for improving the identification rate. In the paper, an algorithm for segmenting the dorsal hand vein image and extracting the vein...
详细信息
An algorithm for dorsal hand vein pattern recognition is presented in the paper. To improve the recognition ratio, the vein skeleton extracting with little distortion is very important. Firstly, the algorithm acquires...
详细信息
This paper proposed the definition of corner saliency firstly, which is an intrinsic characteristic of a corner and denote the contributiveness of a corner on the result of image processing. Then, we discussed the rel...
详细信息
Extracting vein skeleton with little distortion from the vein image is very important for improving the identification rate. In the paper, an algorithm for segmenting the dorsal hand vein image and extracting the vein...
详细信息
ISBN:
(纸本)9781424472352
Extracting vein skeleton with little distortion from the vein image is very important for improving the identification rate. In the paper, an algorithm for segmenting the dorsal hand vein image and extracting the vein skeleton is presented. Firstly, after gray and size normalizing, Gaussian low pass filter and median filter are used to eliminate the speck noise and the horizontal strip scanning noise respectively. Then, an improved NiBlack algorithm segments the vein pattern and an area thresholding algorithm removes the noise blocks from the vein pattern. Subsequently, opening, closing and median filter are used to smooth the vein boundary. After that, the vein pattern is thinned by Kejun Wang's improved conditional thinning. Lastly, a pruning algorithm is presented to trim the spurs and the vein pattern is skeletonized. Experiment shows the algorithm acquires more real skeleton.
An algorithm for dorsal hand vein pattern recognition is presented in the paper. To improve the recognition ratio, the vein skeleton extracting with little distortion is very important. Firstly, the algorithm acquires...
详细信息
An algorithm for dorsal hand vein pattern recognition is presented in the paper. To improve the recognition ratio, the vein skeleton extracting with little distortion is very important. Firstly, the algorithm acquires a clean, one-pixel-width skeleton with little distortion after a series of processes: size and gray normalizing, Gaussian lowpass and median filtering, NiBlack local dynamic thresholding segmenting, area thresholding, morphological opening and closing, median filtering, conditional thinning, spurs pruning. Then, the seven corrected moment invariants of the vein skeleton are extracted as the feature vector. At last, the feature vector is input into SVM for training and recognition. Experiment shows the algorithm achieves a higher recognition ratio of 95.5%.
This paper proposed the definition of corner saliency firstly, which is an intrinsic characteristic of a corner and denote the contributiveness of a corner on the result of image processing. Then, we discussed the rel...
详细信息
This paper proposed the definition of corner saliency firstly, which is an intrinsic characteristic of a corner and denote the contributiveness of a corner on the result of image processing. Then, we discussed the relation among the corner saliency, the out-in degree, the angle sequence and the ratio of line-length sequence in detail, and formulate a mathematic model to calculate the corner saliency. Finally, we introduced an experiment to illustrate the calculation of corner saliency. It shows that the proposed model is effective and has practical application value also.
A comparative performance study of eight global thresholding algorithms for particle images were *** the selected eight global thresholding algorithms,three of them were based on gray level histograms,and the remainin...
详细信息
A comparative performance study of eight global thresholding algorithms for particle images were *** the selected eight global thresholding algorithms,three of them were based on gray level histograms,and the remaining ones were based on the histograms of gradient magnitude.
This paper describes a froth image segmentation *** order to determine bubble size,shape and texture information from the froth images,the images have to be *** of the large variation of the froth image patterns and q...
详细信息
This paper describes a froth image segmentation *** order to determine bubble size,shape and texture information from the froth images,the images have to be *** of the large variation of the froth image patterns and quality,it is difficult to existing segmentation ***,we modified and combined different existing image segmentation algorithms to form a new segmentation algorithm for froth images. In the algorithm,we used and modified a thresholding algorithm to automatically detect maximum of bubbles,then perform morphological technique to growing bubble *** over-segmentation problem was resolved by a object merging algorithm based bubble shape *** the paper,three froth image segmentation results are demonstrated,which shows that the developed segmentation is reasonable for froth images.
A comparative performance study of eight global thresholding algorithms for particle images were investigated. Of the selected eight global thresholding algorithms, three of them were based on gray level histograms, a...
详细信息
A comparative performance study of eight global thresholding algorithms for particle images were investigated. Of the selected eight global thresholding algorithms, three of them were based on gray level histograms, and the remaining ones were based on the histograms of gradient magnitude.
In mineral processing, froth characteristics are important for flotation results. To monitor the variation of froth characteristics, an optical system has been developed. In the flotation system, one important procedu...
详细信息
In mineral processing, froth characteristics are important for flotation results. To monitor the variation of froth characteristics, an optical system has been developed. In the flotation system, one important procedure for image processing and analysis is image segmentation. This paper presents four newly developed segmentation algorithms for froth images. Results of image segmentation were compared to manual segmentation results, and comparisons show that the newly developed algorithms work well for the tested froth images.
暂无评论