基于顏色和紋理特征的新疆維吾爾醫(yī)植物藥材圖像特征提取與判別分析

　　摘要：目的 對(duì)新疆維吾爾醫(yī)植物藥材圖像進(jìn)行特征提取，并對(duì)所研究特征進(jìn)行分析，探討其在維吾爾醫(yī)藥材圖像分類中的效果，找到適用于維吾爾醫(yī)藥材圖像分類的特征，為基于內(nèi)容的新疆維吾爾醫(yī)藥材圖像的檢索系統(tǒng)奠定基礎(chǔ)。方法 以新疆維吾爾藥材中植物藥的花和葉為研究對(duì)象，先對(duì)圖像進(jìn)行預(yù)處理，進(jìn)而提取顏色和紋理特征作為原始特征，并對(duì)特征進(jìn)行統(tǒng)計(jì)學(xué)分析，運(yùn)用最大類間距法篩選得到圖像分類的主要特征，最后應(yīng)用Bayes判別分析法對(duì)特征的分類能力進(jìn)行評(píng)價(jià)。結(jié)果 將顏色特征和紋理特征篩選后進(jìn)行分類，花類圖像的分類準(zhǔn)確率為85%，葉類圖像的分類準(zhǔn)確率為62%。利用篩選后的特征對(duì)花類圖像的分類效果好于利用原始特征分類的效果。結(jié)論 與原始特征分類比較，運(yùn)用篩選后的特征進(jìn)行分類，對(duì)于判別花類藥材的效果較好。這為進(jìn)一步研究維吾爾醫(yī)藥材圖像分類和完善特征提取方法奠定了基礎(chǔ)。
　　關(guān)鍵詞：新疆維吾爾植物藥材；顏色特征；紋理特征；特征提�。慌袆e分類
　　DOI：10.3969/j.issn.1005-5304.2016.01.018
　　中圖分類號(hào)：R29 文獻(xiàn)標(biāo)識(shí)碼：A 文章編號(hào)：1005-5304（2016）01-0078-04
　　Xinjiang Uygur Medicine Image Feature Extraction and Discriminant Analysis Based on Color and Textural Features YUN Wei-kang1， Murat HAMIT1， YAN Chuan-bo1， Abdugheni KUTLUK1， Asat MATMUSA2， YAO Juan3， YANG Fang1， Elzat ALIP1 （1. College of Medical Engineering Technology， Xinjiang Medical University， Urumqi 830011， China； 2. College of Public Health， Xinjiang Medical University， Urumqi 830011， China； 3. Department of Radiology， First Affiliated Hospital of Xinjiang Medical University， Urumqi 830054， China）
　　Abstract： Objective To extract Xinjiang Uyghur medicine image features and analyze the features； To investigate the image classification effect of the researched features； To find the suitable features for Xinjiang Uyghur medicine image classification； To lay the foundation for content-based medical image retrieval system of Xinjiang Uyghur medicine images. Methods The flowers and leaves of Xinjiang Uyghur medicine were treated as the research objects. First， images were under preprocessing. Then color and textural features were extracted as original features and statistics method was used to analyze the features. Maximum classification distance was used to analyze the main features obtained from image classification. At last， the classification ability of features was evaluated by Bayes discriminant analysis. Results Color and textural features were selected and classified. The correct classification rate of flower images was 85% and the correct classification rate of leaf images was 62%. The classification effect of flower images used by selected features was better than classification effect of original feature. Conclusion Compared with the classification of original features， the classification accuracy of flower medicine is higher through selected features. This research can lay a certain foundation for the further researches on Xinjiang Uyghur medicine images
　　and the improvement of feature extraction methods.

相關(guān)熱詞搜索：維吾爾 特征 判別 新疆 紋理