以四元樹為基礎抽取圖片物件特徵 之 影像檢索

Presentation on theme: "以四元樹為基礎抽取圖片物件特徵 之 影像檢索"— Presentation transcript:

1 以四元樹為基礎抽取圖片物件特徵 之 影像檢索
專題J組 指導教授：曾修宜教授 組員 ： 楊智宇 黃文宣 劉濬毅

2 TABLE OF CONTENT Introduction Image Features 。Color 。Texture Quadtree Decomposition Representative feature extraction 。Vector quantization (VQ) algorithm 。 Representative feature extraction of objects using VQ Implementation

3 Introduction Content-Based Image Retrieval
An application of computer vision to the image retrieval problem, that is, the problem of searching for digital images in large databases

4 Introduction Target 我們想要達到的目的為： 1. 讓程式透過Quadtree可以 縮小人類感官與電腦處理的差距 2. 增加search系列套圖的成功率 3. 減低圖片處理的資料量

5 Image Features - Color HSV 。Hue distinguish colors 。Saturation the percentage of white light that is added to a pure color 。Value perceived light intensity The HSV color model, which is similar to human perception, is most frequently used for retrieval.

6 Image Features - Color RGB (Red Green Blue)

7 Image Features - Texture
Angular Second Moment = Contrast = Correlation = Variance = Entropy =

8 Quadtree Decomposition
An image is divided into rectangular blocks 7x7 is the smallest block we define 7

9

10 Representative feature extraction Vector Quantization (VQ) algorithm
主要概念： 配合前述的Quadtree，把圖片重新分割為block 再把切割出來的block配合之前的Texture公式對應到 一個8-dimension vector space中的座標 再配合Vector Quantization把vector分群

11 Representative feature extraction Representative feature extraction of objects using VQ

12 Representative feature extraction Representative feature extraction of objects using VQ

13 Implementation A Simple Follow Chart

14 Implementation Search Result