An Effective Similarity Measurement Algorithm for Dominant Color Feature Matching in Image Retrieval

2012 ◽  
Vol 182-183 ◽  
pp. 1169-1173
Author(s):  
Li Fang Yang ◽  
Xiang Lin Huang ◽  
Rui Lv ◽  
Hui Lv
Keyword(s):  
Image Retrieval ◽  
Feature Matching ◽  
Color Space ◽  
Similarity Measurement ◽  
Average Precision ◽  
Image Region ◽  
Color Feature ◽  
Color Distribution ◽  
Dominant Color ◽  
Measurement Algorithm

For the reason that dominant colors can characterize color information of image region and can represent the image using fewer dimensions, it is one of the widely used color features in image retrieval. We extract the dominant color feature in HSV color space, and combine it with color distribution information. In this paper, a new similarity measurement algorithm based on block distance is proposed for dominant color matching. Our proposed algorithm not only takes the distance between dominant colors into account, but also the difference of the percentage of dominant colors. The average precision of our algorithm improves about 5% and about 14% respectively compared with block distance and Euclidean distance. Although the average precision of our algorithm is almost equal to quadratic form distance, the computation cost of our algorithm is obviously less than it.

Fast Image Retrieval Prototype using Color Descriptor

2016 ◽  
Vol 1 (22) ◽  
pp. 745-758
Author(s):  
Bushra Abdul-Kareem Abdul-Azeez
Keyword(s):  
Image Retrieval ◽  
Color Space ◽  
Image Database ◽  
Query Image ◽  
Color Feature ◽  
Retrieval Time ◽  
Dominant Color ◽  
Color Descriptor

In recent years, image retrieval prototypes become important and increased noticeably. Color feature is one of the most significant features to represent image. In this paper, we use a Dominant Color (DC) feature to represent images where each image represented by 8-DCs as maximum. Based on DCs values, image database is indexed using 3-D RGB partitioning color space. This is to reduce searching process where once a query image is given to the prototype; it will not search the whole database. Proposed technique will identify the partition and search the image within this partition only. According to the proposed method, extensive experiments were conducted on Corel databases. As a result, the retrieval time is reduced significantly without degradation to precision of retrieval.

scholarly journals Content-Based Image Retrieval using Color Quantization and Angle Representation

2014 ◽  
Vol 13 (10) ◽  
pp. 5094-5104
Author(s):  
Ihab Zaqout
Keyword(s):  
Image Retrieval ◽  
Color Space ◽  
Measurement Methods ◽  
Content Based Image Retrieval ◽  
Similarity Measurement ◽  
Color Quantization ◽  
Human Visual Perception ◽  
Hsv Color Space ◽  
Perception System ◽  
Similar Images

An efficient non-uniform color quantization and similarity measurement methods are proposed to enhance the content-based image retrieval (CBIR) applications. The HSV color space is selected because it is close to human visual perception system, and a non-uniform color method is proposed to quantize an image into 37 colors. The marker histogram (MH) vector of size 296 values is generated by segmenting the quantized image into 8 regions (multiplication of 45°) and count the occurrences of the quantized colors in their particular angles. To cope with rotated images, an incremental displacement to the MH is applied 7 times. To find similar images, we proposed a new similarity measurement and other 4 existing metrics. A uniform color quantization of related work is implemented too and compared to our quantization method. One-hundred test images are selected from the Corel-1000 images database. Our experimental results conclude high retrieving precision ratios compared to other techniques.

Image retrieval of wool fabric. Part III: based on aggregated convolutional descriptors and approximate nearest neighbors search

2021 ◽  
pp. 004051752110371
Author(s):  
Ning Zhang ◽  
Jun Xiang ◽  
Lei Wang ◽  
Weidong Gao ◽  
Ruru Pan
Keyword(s):  
Image Retrieval ◽  
Nearest Neighbors ◽  
Search Method ◽  
Similarity Measurement ◽  
Wool Fabric ◽  
Search Performance ◽  
Color Feature ◽  
Material Resources ◽  
Elapsed Time ◽  
Approximate Nearest Neighbors

For sample reproduction, texture and color are both significant when the consumer has no specific or individual demands or cannot describe the requirements clearly. In this paper, an effective method based on aggregated convolutional descriptors and approximate nearest neighbors search was proposed to combine the texture and color feature for wool fabric retrieval. Aggregated convolutional descriptors from different layers were combined to characterize the wool fabric image. The approximate nearest neighbors search method Annoy was adopted for similarity measurement to balance the trade-off between the search performance and the elapsed time. A wool fabric image database containing 82,073 images was built to demonstrate the efficacy of the proposed method. Different feature extraction and similarity measurement methods were compared with the proposed method. Experimental results indicate that the proposed method can combine the texture and color feature, being effective and superior for image retrieval of wool fabric. The proposed scheme can provide references for the worker in the factory, saving a great deal of labor and material resources.

Color Extraction and Research of Image Retrieval Based on Wavelet Territory

2014 ◽  
Vol 631-632 ◽  
pp. 418-421
Author(s):  
Lin Lin Song ◽  
Qing Hu Wang ◽  
Zhi Li Pei
Keyword(s):  
Wavelet Transform ◽  
Image Retrieval ◽  
Low Frequency ◽  
Histogram Method ◽  
Color Feature ◽  
Dominant Color ◽  
Color Features ◽  
Human Eyes

This paper firstly studies the image color features based on wavelet territory. We introduce a color features’ extract method based on HSI low-frequency subband color features after partition. Firstly, according to the image attention from human eyes, we split the image into sub-blocks. Then extract HSI low-frequency subband color features of each sub-block after wavelet transform, and we can obtain the image color features by weighting. Comparing with traditional histogram method, the experiment results show that the proposed algorithm based on weighted dominant color feature has better retrieval precision.

scholarly journals Implementation of Adaptive Real-Time Camouflage System in Visible-Light Band

2021 ◽  
Vol 11 (15) ◽  
pp. 6706
Author(s):  
Liying Zhen ◽  
Yan Zhao ◽  
Pin Zhang ◽  
Congwei Liao ◽  
Xiaohui Gao ◽  
...  
Keyword(s):  
Evaluation Method ◽  
Pulse Width Modulation ◽  
Feature Matching ◽  
Local Environment ◽  
Color Feature ◽  
Matching Algorithm ◽  
Central Processing ◽  
Dominant Color ◽  
Waveform Generation ◽  
Driving Waveform

This paper presents an adaptive camouflage system in visible band, featuring a dominant color feature-matching algorithm and pulse width modulation (PWM)-based display driving circuit. The control system consists of three parts, namely, the background sensing part, the central processing part, and the physical driving waveform generation part. Images of the local environment are sampled by the background sensing part, and then the dominant color feature matching algorithm is conducted to select a proper camouflage image that matches the local environment. Consequently, the cholesteric liquid crystals (CLCs) display using amplitude adjustable AC voltage, which is modulated by the physical driving waveform generation unit. The experimental results show that the matching degree of the proposed algorithm was 2.47 times that of the conventional hue (H), saturation (S), and value (V) histogram camouflage evaluation method, while the output peak wavelength of the reflective band can be adjusted from 604 to 544 nm according to the ambient color profile.

scholarly journals Content Based Image Retrieval Berdasarkan Fitur Low Level: Literature Review

2017 ◽  
Vol 8 (2) ◽  
Author(s):  
Rahmad Hidayat ◽  
Agus Harjoko ◽  
Anny Kartika Sari
Keyword(s):  
Image Retrieval ◽  
Color Space ◽  
Human Perception ◽  
Image Features ◽  
Content Based Image Retrieval ◽  
Gray Level ◽  
Color Feature ◽  
Low Level ◽  
Abstract Content ◽  
Color Texture

Abstract. Content-based Image Retrieval (CBIR) is an image search process by comparing the image features sought by the images contained in the database. Low-level features in the image are commonly used in CBIR is the color, texture, and shape. This article conducts a review of journals related to CBIR, particularly research based on low-level features. The journals are then classified based on the color space, features and feature extraction methods. The results show that the color space often used is the RGB and HSV due to their compatibility with the hardware and human perception of color. The features most often used in CBIR is the color feature. This is due to the fact that color features can easily and quickly be extracted. The most often used method to extract the color feature is the color histogram, the most common method used to extract texture features is the gray level co-occurence matrix, and the method most widely used to extract the shape feature is canny edge.Keywords: CBIR, color, texture, shape. Abstract. Content based Image Retrieval (CBIR) merupakan proses pencarian gambar dengan membandingkan fitur-fitur yang terdapat pada gambar yang dicari dengan gambar yang terdapat dalam basis data. Fitur-fitur low level pada gambar yang biasa digunakan dalam CBIR adalah warna, tekstur, dan bentuk Artikel ini melakukan tinjauan terhadap penelitian-penelitian yang berkaitan dengan CBIR, khususnya penelitian yang berbasis pada fitur low level. Penelitian-penelitian tersebut kemudian diklasifikasikan berdasarkan ruang warna, fitur dan metode ekstraksi fitur. Hasil tinjauan menunjukkan bahwa ruang warna yang sering digunakan adalah RGB dan HSV karena dianggap cocok dengan hardware dan persepsi manusia terhadap warna. Adapun fitur yang paling sering digunakan dalam CBIR adalah fitur warna. Hal ini disebabkan fitur warna mudah dan cepat diekstraksi. Metode yang paling sering digunakan untuk mengekstraksi fitur warna adalah histogram warna, metode yang paling sering digunakan untuk mengekstraksi fitur tekstur adalah gray level co-occurence matrix, dan metode yang paling banyak digunakan untuk, mengekstraksi fitur bentuk adalah canny edge.Kata kunci: CBIR, warna, tekstur, bentuk.

An Image Retrieval Algorithm Based on HVS Weighted Color Features

2014 ◽  
Vol 631-632 ◽  
pp. 410-413
Author(s):  
Lin Lin Song ◽  
Qing Hu Wang ◽  
Zhi Li Pei
Keyword(s):  
Visual System ◽  
Image Retrieval ◽  
Human Visual System ◽  
Retrieval Algorithm ◽  
Histogram Method ◽  
Color Feature ◽  
Dominant Color ◽  
Color Features

This paper introduces a HVS Weighted color features’ extract method. Firstly, we split the image into sub-blocks and draw the color feature consists of dominant colors in each sub-block. Then weighting the gained color features by making use of Human Visual System. So we can obtain the weighted dominant color feature. Comparing with traditional histogram method and split blocks dominant color method, the experiment results show that the proposed algorithm based on weighted dominant color feature has better retrieval precision.

Sign in / Sign up

Export Citation Format

Share Document