Better image texture recognition based on SVM classification

Author(s):  
Kuan Liu ◽  
Bin Lu ◽  
Yaxun Wei
Author(s):  
YING SHAN ◽  
HARPREET S. SAWHNEY ◽  
ART POPE

We propose a novel similarity measure of two image sequences based on shapeme histograms. The idea of shapeme histogram has been used for single image/texture recognition, but is used here to solve the sequence-to-sequence matching problem. We develop techniques to represent each sequence as a set of shapeme histograms, which captures different variations of the object appearances within the sequence. These shapeme histograms are computed from the set of 2D invariant features that are stable across multiple images in the sequence, and therefore minimizes the effect of both background clutter, and 2D pose variations. We define sequence similarity measure as the similarity of the most similar pair of images from both sequences. This definition maximizes the chance of matching between two sequences of the same object, because it requires only part of the sequences being similar. We also introduce a weighting scheme to conduct an implicit feature selection process during the matching of two shapeme histograms. Experiments on clustering image sequences of tracked objects demonstrate the efficacy of the proposed method.


2014 ◽  
Vol 631-632 ◽  
pp. 399-402
Author(s):  
Liu Juan ◽  
Xin Zheng

We adopt a fast image texture recognition technology to identify whether an image for texture image, Then we extract the texture feature for image texture, and to extract the color features for Non-texture images, By classifying different types of image retrieval to improve retrieval efficiency. The experimental results show that, this method of the rapid texture recognition technology can greatly improve the accuracy of image retrieval, and it has a great effect in terms of speed.


2019 ◽  
Vol 1 (1) ◽  
pp. 15-22
Author(s):  
Suhendri Suhendri ◽  
Putri Rahayu

The color and shape of leaves each different plant water rose so that it can be found a certain texture to classify. This study uses an image texture recognition leaves to be classified. Leaves used are three types of guava leaves, Bunton 3 Green Guava, Guava and Guava image Bol. Feature extraction process used a method is Gray Level Co-Occurrence Matrix (GLCM) with Matlab tool. GLCM is used to retrieve the value of the image attribute or value matrix. This study uses a Neural Network algorithm with a tool RapidMiner. One alternative solution to the above problems is by way of classifying types of guava leaf water by looking at the characteristics of the water guava leaves. Leaf is one of the characteristics of the plant that is easily recognizable. The classification process is to produce a good accuracy value against bunton guava leaves 3 green, pink bol, and guava image. The results showed that the level of accuracy in the guava leaf bol is 81.25%, bunton leaves 3 Green 75%, and 80% leaf image and the total value of the overall accuracy of 78.89%. Thus the above results show that the value of the accuracy of the resulting research shows three types of guava leaf water has been classified and deserves to be investigated.


Sign in / Sign up

Export Citation Format

Share Document