This paper exposes a analysis of weed detection based on color and texture features over images of crops, focus on provide a technological tool to support farmers in their maintenance tasks. Image processing technique has become a promising tool for precise real time weed and crop detection in field. This work presents a machine vision system for weed detection in vegetable crops using outdoor images, avoiding lighting and sharpness problems during acquisition step. The various steps of weed detection are pre-processing, segmentation, feature extraction and classification. In the previous work, technique of linear interpolation is applied for the weed detection which results in the low accuracy. To improve accuracy for the weed detection, technique of cluster based segmentation, textural feature and KNN classification is applied. The proposed method is implemented in MATLAB and results are analyzed in terms of accuracy and execution time.