Segmentation and Feature Extraction of Flowers Intended for Image Retrieval : A survey
Aparna S. Patil, Jermin Shaikh · 2016
Flower image retrieval is a very important step for computer-aided plant species identification. The paper elaborates the segmentation technique and feature extraction schema proposed by different authors. Firstly the flower area is extracted from the background image using OTSU thresholding, then the Improved Itti Model is used to extract the features like color, texture, shape. Otsu algorithm can obtain satisfactory segmentation results when it is applied to the noisy images. We use the histogram intersection distance to measure the similarity between the different images.To show the degree of similarity between two images extracted features of query image and target image are recorded. Finally, classification contains the database and does the comparison of flowers under the same category.