HSV-based Color Texture Image Classification using Wavelet Transform and Motif Patterns

Department of Computer Science and Engineering, National Chung Hsing University, 402, Taichung, Taiwan, ROC
Journal of Computers 01/2010; 20(4).


In this paper, a novel color texture image classification based on HSV color space, wavelet trans-form, and motif patterns is introduced. Traditionally, RGB color space is widely used in digital images and hardware. However, RGB color space is not accurate in human visual perception and statistical analysis. Therefore, HSV color space is applied to obtain more accurate color statistics for extracting features. Due to extracting texture features in color texture images, wavelet transform and motif co-occurrence matrix are used in HSV color space for feature extraction. According to characteristic of wavelet transform, the horizon-tal, vertical and diagonal distributions are presented in sub-bands of a transformed image. Then, texture fea-tures of the horizontal, vertical and diagonal sub-bands are extracted by the motif co-occurrence matrix. After feature extraction, support vector machine (SVM) is applied to learn and classify texture classes by the ex-tracted features. From experimental results, the proposed method is better and more correct than recent RGB-based color texture image classification.


Available from: Jun-Dong Chang, Feb 23, 2015
  • [Show abstract] [Hide abstract]
    ABSTRACT: Shortness of breath is a frequent reason for patients to request prehospital emergency medical services and is a symptom of many life-threatening conditions. To date, there is limited information on the epidemiology of, and outcomes of patients seeking emergency medical services for, shortness of breath in India. This study describes the characteristics and outcomes of patients with a chief complaint of shortness of breath transported by a public ambulance service in the state of Andhra Pradesh, India. This prospective, observational study enrolled patients with a chief complaint of shortness of breath during twenty-eight, 12-h periods. Demographic and clinical data were collected from emergency medical technicians using a standardized questionnaire. Follow-up information was collected at 48-72 h and 30 days. Six hundred and fifty patients were enrolled during the study period. The majority of patients were male (63%), from rural communities (66%), and of lower socioeconomic status (78%). Prehospital interventions utilized included oxygen (76%), physician consultation (40%), i.v. placement (15%), nebulized medications (13%), cardiopulmonary resuscitation (5%), and bag-mask ventilation (4%). Mortality ratios before hospital arrival, at 48-72 h, and 30 days were 12%, 27%, and 35%, respectively. Forty-six percent of patients were confirmed to have survived to 30 days. Predictors of death before hospital arrival were symptoms of chest pain (16% vs. 12%; p < 0.05) recent symptoms of upper respiratory infection (7.5% vs. 4%; p < 0.05), history of heart disease (14% vs. 7%; p < 0.05), and prehospital hypotension, defined as systolic blood pressure <90 mm Hg (6.3% vs. 3.7%; p < 0.05). Among individuals seeking prehospital emergency medical services in India, the chief complaint of shortness of breath is associated with a substantial early and late mortality, which may be in part due to the underutilization of prehospital interventions. Copyright © 2015 Elsevier Inc. All rights reserved.
    Journal of Emergency Medicine 05/2015; DOI:10.1016/j.jemermed.2015.02.041 · 0.97 Impact Factor