scholarly journals Analisis Seleksi Citra Mirip dengan Memanfaatkan Konsep CBIR dan Algoritma Threshold

2011 ◽  
Vol 2 (2) ◽  
pp. 715
Author(s):  
Abdul Haris Rangkuti
Keyword(s):  
Fuzzy Logic ◽  
Image Retrieval ◽  
Image Database ◽  
Threshold Value ◽  
Color Histogram ◽  
Query Image ◽  
Content Base Image Retrieval ◽  
Comparison Results ◽  
Sorting Process ◽  
The One

Content base image retrieval (CBIR) is the concept of image retrieval by comparing the existing image on the sample to that of the database (query by example). CBIR process based on color is carried out using adaptive color histogram concept, while one based on shape is performed using moment concept. Following up the process results, a sorting process is done based on a threshold value of the sample image through the utilization threshold algorithm. The image displayed is be sorted from the one that is nearly similar to the query image (example) to the resemblance of the lowest (aggregation value). The threshold value of the query image used as reference is compared with the aggregation value of the image database. If the comparison in the search for similarities by using the concept of fuzzy logic approaches 1, the comparison between the threshold value and the aggregation value is almost the same. Otherwise, if it reaches 0, the comparison results in a lot of differences. 

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 Convolutional neural networks for relevance feedback in content based image retrieval

2020 ◽  
Vol 79 (37-38) ◽  
pp. 26995-27021
Author(s):  
Lorenzo Putzu ◽  
Luca Piras ◽  
Giorgio Giacinto
Keyword(s):  
Image Retrieval ◽  
Relevance Feedback ◽  
Image Representation ◽  
Semantic Gap ◽  
Content Based Image Retrieval ◽  
Data Sets ◽  
Great Success ◽  
Query Image ◽  
Pros And Cons ◽  
The One

Abstract Given the great success of Convolutional Neural Network (CNN) for image representation and classification tasks, we argue that Content-Based Image Retrieval (CBIR) systems could also leverage on CNN capabilities, mainly when Relevance Feedback (RF) mechanisms are employed. On the one hand, to improve the performances of CBIRs, that are strictly related to the effectiveness of the descriptors used to represent an image, as they aim at providing the user with images similar to an initial query image. On the other hand, to reduce the semantic gap between the similarity perceived by the user and the similarity computed by the machine, by exploiting an RF mechanism where the user labels the returned images as being relevant or not concerning her interests. Consequently, in this work, we propose a CBIR system based on transfer learning from a CNN trained on a vast image database, thus exploiting the generic image representation that it has already learned. Then, the pre-trained CNN is also fine-tuned exploiting the RF supplied by the user to reduce the semantic gap. In particular, after the user’s feedback, we propose to tune and then re-train the CNN according to the labelled set of relevant and non-relevant images. Then, we suggest different strategies to exploit the updated CNN for returning a novel set of images that are expected to be relevant to the user’s needs. Experimental results on different data sets show the effectiveness of the proposed mechanisms in improving the representation power of the CNN with respect to the user concept of image similarity. Moreover, the pros and cons of the different approaches can be clearly pointed out, thus providing clear guidelines for the implementation in production environments.

scholarly journals Content-Based Image Retrieval System for Real Images

10.29007/w4sr ◽  
2018 ◽  
Author(s):  
Yin-Fu Huang ◽  
Bo-Rong Chen
Keyword(s):  
Image Retrieval ◽  
Retrieval System ◽  
Image Database ◽  
Multimedia Data ◽  
Content Based Image Retrieval ◽  
Real Image ◽  
Query Image ◽  
Image Retrieval System ◽  
Similar Images ◽  
Network Technologies

With the rapid progress of network technologies and multimedia data, information retrieval techniques gradually become content-based, and not text-based yet. In this paper, we propose a content-based image retrieval system to query similar images in a real image database. First, we employ segmentation and main object detection to separate the main object from an image. Then, we extract MPEG-7 features from the object and select relevant features using the SAHS algorithm. Next, two approaches “one-against- all” and “one-against-one” are proposed to build the classifiers based on SVM. To further reduce indexing complexity, K-means clustering is used to generate MPEG-7 signatures. Thus, we combine the classes predicted by the classifiers and the results based on the MPEG-7 signatures, and find out the similar images to a query image. Finally, the experimental results show that our method is feasible in image searching from the real image database and more effective than the other methods.

scholarly journals Unsupervised Content Based Image Retrieval by Combining Visual Features of an Image With A Threshold

2012 ◽  
pp. 149-154
Author(s):  
S. M. Zakariya ◽  
Rashid Ali ◽  
Nesar Ahmad
Keyword(s):  
Image Retrieval ◽  
Retrieval System ◽  
Image Database ◽  
The Other ◽  
Content Based Image Retrieval ◽  
Visual Features ◽  
Query Image ◽  
System A ◽  
Image Retrieval System

Content-based image retrieval (CBIR) uses the visual features of an image such as color, shape and texture to represent and index the image. In a typical content based image retrieval system, a set of images that exhibit visual features similar to that of the query image are returned in response to a query. CLUE (CLUster based image rEtrieval) is a popular CBIR technique that retrieves images by clustering. In this paper, we propose a CBIR system that also retrieves images by clustering just like CLUE. But, the proposed system combines all the features (shape, color, and texture) with a threshold for the purpose. The combination of all the features provides a robust feature set for image retrieval. We evaluated the performance of the proposed system using images of varying size and resolution from image database and compared its performance with that of the other two existing CBIR systems namely UFM and CLUE. We have used four different resolutions of image. Experimentally, we find that the proposed system outperforms the other two existing systems in ecery resolution of image.

scholarly journals A Review on LBP in Image Retrieval System for Future Enhancement and Vector Images

2020 ◽  
pp. 155-161
Author(s):  
K Rajalakshmi ◽  
V Krishna Dharshini ◽  
S Selva Meena
Keyword(s):  
Image Retrieval ◽  
Image Database ◽  
Content Based Image Retrieval ◽  
Large Set ◽  
Query Image ◽  
Matching Algorithm ◽  
Image Retrieval System ◽  
Similar Images ◽  
Vector Images ◽  
Similar Kind

Content-Based Image Retrieval is a process to retrieve the similar images from the large set of image database corresponding to the query image. In CBIR low level or pixel level features such as color, texture and shape of the images are extracted and on the basis of similarity matching algorithm the required similar kind of images are retrieved from the image database. To understand the evaluation and evolution of CBIR system various research was studied and various research is going on this way also. In this paper, we have discussed some of the popular pixel level feature extraction techniques for Content-Based Image Retrieval and we also present here about the performance of each technique.

scholarly journals Design of Feature Extraction in Content Based Image Retrieval (CBIR) using Color and Texture

2012 ◽  
pp. 157-161
Author(s):  
Swati V. Sakhare ◽  
Vrushali G. Nasre
Keyword(s):  
Feature Extraction ◽  
Image Retrieval ◽  
Image Database ◽  
Color Histogram ◽  
Content Based Image Retrieval ◽  
Visual Features ◽  
Efficient Approach ◽  
Novel Method ◽  
Fuzzy Color Histogram ◽  
Color Texture

Retrieval of images based on visual features such as color, texture and shape have proven to have its own set of limitations under different conditions. Various techniques have been implemented using these features like fuzzy color histogram, Tammura texture etc. In this paper we propose a novel method with highly accurate and retrieval efficient approach which will work on large image database with varied contents and background.

scholarly journals Seleksi Citra Berdasarkan Ciri dengan Algoritma Threshold Mengunakan Fuzzy Kurva S dan Fungsi Min

2012 ◽  
Vol 3 (1) ◽  
pp. 254
Author(s):  
A. Haris Rangkuti
Keyword(s):  
Image Retrieval ◽  
Threshold Value ◽  
Sigmoid Function ◽  
Histogram Method ◽  
Query Image ◽  
Fuzzy Function ◽  
Euclidean Distance Function ◽  
S Curve ◽  
Image Query ◽  
Image Euclidean Distance

Image retrieval process of fruits and flowers with CBIR concept was represented by the colors and shapes using adaptive histogram method for color, and invariant moment for shape. To measure the similarity between the query image and the basis data image Euclidean distance function was used, where the result is f(x). Calculations for f (y) through the process of ‘fuzzy-ing’-S curve, where the value of f(x) guides the sigmoid function. The value f(y) on each image than the threshold value based image query. Basically, the algorithm displays the image based on Threshold features, by comparing the threshold value with the value f(y). A high grade value (approaching 1) indicates that the feature of the sample (query) image is similar to the basis data image, and vice versa. The process was continued by comparing the value grades of the image representation of color and form using min operator in fuzzy logic, so that it only displayed several images that have some resemblances in accordance with the original image. The advantage of threshold algorithm and the fuzzy function - compared to other methods – lies in the simplicity method in the image retrieval, so that the performance of CBIR becomes more reliable and effective.

scholarly journals CBIR SYSTEM USING COLOR HISTOGRAM AND WAVELET TRANSFORM FOR BLOOD CELLS IMAGES

2012 ◽  
pp. 8-11
Author(s):  
C. Rubina ◽  
S. Dasu
Keyword(s):  
Image Retrieval ◽  
Blood Cells ◽  
Color Histogram ◽  
Content Based Image Retrieval ◽  
Prototype System ◽  
Medical Field ◽  
Query Image ◽  
Cell Image ◽  
Current Content ◽  
Research Goal

The research in Content-based image retrieval is developing rapidly. It benefits many other fields, in particular the medical field as the need of having a better way of managing andretrieving digital images has increased.The aim of the thesis is to investigate performance of descriptors of blood cell image retrieval. In this process traditional wavelet based and global color histogram is investigated. The prototype system allows user to search by providing a query image and selecting one of four implemented methods. Research goal is enhancing current content-based image retrieval techniques. Results were obtained by experimenting to this proposed method is able to perform clinically relevant queries on image databases without user supervision.

scholarly journals A new approach towards Image retrieval using texture statistical methods

2018 ◽  
Vol 2 (1) ◽  
pp. 13
Author(s):  
R Tamilkodi ◽  
G. Rosline Nesa Kumari ◽  
S. Maruthu Perumal
Keyword(s):  
Image Retrieval ◽  
Statistical Methods ◽  
Image Database ◽  
New Method ◽  
Query Image ◽  
New Approach ◽  
Energy Entropy ◽  
Retrieval Result ◽  
Canberra Distance ◽  
Texture Characterization

Texture is a possession that represents the facade and arrangement of an image. Image textures are intricate ocular patterns serene of entities or regions with sub-patterns with the kind of brightness, color, outline, dimension, and etc.This article proposes a new method for texture characterization by using statistical methods (TCUSM). In this proposed method (TCUSM) the features are obtained from energy, entropy, contrast and homogeneity. In an image, each one pixel is enclosed by 8 nearest pixels. The confined in turn for a pixel can be extracted from a neighbourhood of 3x3 pixels, which represents the fewest absolute unit. We used four vector angles 0, 45, 90,135 to carry out the experimentation with the query image. A total of 16 texture values are calculated per unit. Compute the feature vectors for the query image by calculating texture unit and the resultant value is compared with the image database. The retrieval result shows that the performance using Canberra distance has achieved higher performance. 

Study of Feature Apprehension Using Soft Computing Approaches

2018 ◽  
pp. 170-190
Author(s):  
Deepika Dubey ◽  
Deepika Singh Kushwah ◽  
Deepanshu Dubey
Keyword(s):  
Neural Networks ◽  
Image Processing ◽  
Fuzzy Logic ◽  
Soft Computing ◽  
Region Of Interest ◽  
Image Database ◽  
The Other ◽  
Soft Computing Techniques ◽  
Similar Images ◽  
The One

An image may be mist full for the one or may be nostalgic for the other. But for a researcher, each image is distinguished on the basis of its low-level features like color, shape, size. Other features like edges, corner/interesting points, blobs/region of interest, ridges, etc. can also be used for computation purpose. Using these features distinctions, an image can be processed for the purpose of enhancing the images having same features, matching, and shortlisting of similar images from a random available image database. This could be done using soft computing techniques like neural networks, fuzzy logic, and evolutionary computation methods. Neural networks can participate effectively in image processing in several ways.

Sign in / Sign up

Export Citation Format

Share Document