Abstract: In the cutting logging process，how to recognize the cuttings automatically ，quickly and correctly is very important．A cutting recognition algorithm based on Gabor filter and SVM was proposed to resolve this problem． The algorithm used
Gabor filter to get the cuttings^' features．Then the features were used to train the support vector machine classifier and the cuttings were classified by using the trained support vector machine．Using the algorithm，after logged 4 wells of Luodai gas reservoir，a high recognition rate can be reached at 90%． The experimental results demonstrate the algorithm is feasible，robust and applicable．

Key words: Cutting recognition , Support vector machine , Texture , Gabor filter

摘要： 针对在随钻过程中如何自动、快速、准确地识别岩屑的问题，对岩屑的纹理进行了深入的分析研究，采用Gabor滤波器对不同岩性的岩屑图像进行纹理提取和分析，提取了反映不同岩屑图像纹理结构的特征参数，最后将支持向量机应用到岩屑的识别过程中，取得了较好的识别效果。通过对四川洛带气田4口井的现场随钻，结果证明算法识别正确率达到90%以上，为快速自动录井提供了一条有效的途径。

关键词: 岩屑识别 , 支持向量机 , 纹理 , Gabor 滤波器