Retrieve Images Based On Dominant Colors Computer Science Essay

Published:

This essay has been submitted by a student. This is not an example of the work written by our professional essay writers.

This paper proposes the method to retrieve images based on dominant colors in the foreground image. This Paper looks into the image retrieval technique based on color . In order to access this information, an effective retrieval technique is required. The foreground of the image only gives semantics compared to the background of the image. This is the central theme of the proposed work.

[1] "Our world is dominated by visual information and a tremendous amount of such information is being added day by day". It could be unrealistic to adapt to this eruption of superficial information, unless they are composed such that recovery of them effectively and successfully is conceivable.

Content based Image recovery is a swearing methodology to pursuit through a image or picture database by means of image or picture features namely color, texture, shape, design, pattern or any mixed combinations of them. Color is an essential sign for picture pr image retrieval. Color not just adds delightfulness to representations and yet gives more informative data, which is utilized as a compelling apparatus within substance based representation recovery. In Color Indexing, for any given Query picture the objective is to recover or retrieve every last trace of the representations whose color is comparable to the aforementioned of question picture.

The existing Content Based Image Retrieval Systems based on dominant color technique do not separate the foreground of the image from the background of the image. As a result, there is a chance of considering the background as the dominant color region even though that doesn’t provide any semantics to the image. It is the foreground of the image that gives semantics, not the background of the image.

The proposed system is a stand-alone system. The user can maintain a database of images of various formats. He can add and delete the images of his choice. For every image that is present in the database, the dominant color of its foreground object is stored. To retrieve images, the user has to provide a query image to the system. As a result, the images which are similar to the query image will be displayed in such a way that the most similar image will be displayed first followed by the next similar image and so on.

Background.

Existing System:

Inexpensive image-capture and storage technologies have allowed massive collections of digital images to be created. However, as [2] the database grows, the difficulty in order to find a relevant image increases. The most used traditional and common method of image retrieval is to utilize some method of adding metadata such as keywords, captions or descriptions to the images so that retrieval can be performed over the annotation words.[3] Manual image annotation is a time-consuming process. [4] It is laborious and expensive. To overcome this, Content Based Image Retrieval (CBIR) is introduced, which aims at avoiding the use of textual descriptions and instead retrieves images based on their visual similarity to a user-supplied query image. This proposed project aims to develop one such Content Based Image Retrieval System.

Proposed System

The proposed system is a stand-alone system. The user can maintain a database of images of numerous formats. He can add, delete, retrive the images of his choice. For every image that is present in the database, the dominant color of its foreground object is stored. In order to retrieve images, the user has to provide a query image to the system. With respect to this query image, the images which are similar to the query image will be displayed in such a way that the most similar image will be displayed first followed by the next similar image and so on.

So far, Content Based Image Retrieval has not been implemented as a general image search. It has been implemented in specific application areas like Photograph archives, Retail Catalogs, Medical Diagnosis, Crime Prevention etc. In such cases, the images are of similar category. But we are implementing it as a general image retrieval technique. Different types of images are available in the database. So while adding images, we store them under different categories.

Aim: The aim of the proposed project is to research into the image retrieval techniques and to analyze the problem by giving a query image and to design an approach by using various algorithms that are required and implement a product that gives the accurate image retrieval against the given query image and test the product against huge number of query images.

Objectives

To research about various retrieval methods using journals, books and online sources.

To plan and carry out experiments by using a query image.

To design appropriate algorithm and use them where ever necessary.

To develop a prototype for image retrieval from the data base using algorithm.

To test the prototype using suitable experiments by using a query image

Purpose of the System

Inexpensive image-capture and storage technologies have allowed massive collections of digital images to be created. As the database grows, the difficulty of finding relevant images increases. Most traditional and common method of image retrieval uses a method of adding metadata such as Keywords, captions, or descriptions to the images so that retrieval can be performed over the annotation words. Manual annotation of image is time-consuming, expensive and laborious. To address this, Content Based Image Retrieval (CBIR), which aims at avoiding the use of textual descriptions and instead retrieves images based on their visual similarity to a user-supplied query image. This proposed project aims project aims to develop one such Content Based Image Retrieval System.

Scope of the System

This software system is a Content Based Image Retrieval System. Content Based Image Retrieval techniques mainly use image features for the retrieval of image retrieval. The main features that is used for image retrieval are color, texture and shape. This proposed project deals with the image retrieval technique based on color. This proposed project implements the method to retrieve images based on dominant color in the foreground objects.

More specifically, this system is a stand-alone system. It contains a large database of images. It retrieves the images whose dominant color in the foreground objects matches with that of the query image supplied by the user.

INTELLECTUAL CHALLENGE

The challenges for the proposed project include implementing the design. The main challenge is to renovate the old techniques that are being used. The main problem is to implement the system cost effectively. Another problem is that there is a chance of confusion to occur in the concepts of algorithms. This may occur mostly due to the lack of proper understanding of the concept.

Research:

Disadvantages of Earlier Image Retrieval Systems

Before introducing the fundamental theory of content based image retrieval, we will take a brief look at its development. Initial work on image retrieval can be traced back to the late 1970s. [5] In 1979, there was a conference that took place in Florence, on Database Techniques for Pictorial Applications. Since then, the application potential of image database management techniques has attracted the attention of many researchers. Early techniques did not include advanced features like visual features but they were implemented on the textual annotation of images.[6] In other words, representations were first expounded with content then after that looked utilizing a text-based methodology from conventional database administration frameworks. Text-based image retrieval uses traditional database techniques to manage images. [7] by the use of text descriptions, images can be organized by topical or semantic hierarchies to facilitate easy access, browsing and navigation based on standard Boolean queries. Since, automatically generated descriptive texts for a wide spectrum of images is not feasible, so most of the text-based image retrieval systems require manual annotation of images. Annotating images manually is an expensive and cumbersome task for huge image databases, and is often, context-sensitive, subjective and incomplete. As a result, it is difficult for the traditional text-based methods to support a variety of task-dependent queries.

Due to the above mentioned disadvantage there arose a situation where there is much need to implement a new approach. Thus the new approach that came into power is Content Based Image Retrieval.

Content Based Image Retrieval.

Content based image recovery, a method which utilizes visual substance to venture representations from vast scale image databases according to users interest, has been an active and quick progressing research area in 1990s. Throughout the past decade, striking advancement has been made in both theoretical research and system development. However there remain numerous challenging research situations that continues to attract various developers and researches from different disciplines.

They are certain basic approaches for Content Based Image Retrieval are :

1. Conventional Histogram-based Matching

2. Dominant Color Region based Indexing

1. Conventional Histogram-based Matching

[8] The histogram-based method is very suitable for color image retrieval because they are invariant to geometrical information in images, such as translation and rotation. Histogram intersection method is to measure the intersection area between two images' histograms. They are usually named as reference image (R) for the query input and model images (M) from the image database. Similarity measure between R and M is then performed by calculating the histogram intersection I(R,M). The larger the value I(R,M) the more similar the images R and M is. Images M could then be ranked from the image database. The same color distribution histograms between different brightness conditions of the two digital images result in smaller intersection value and make the highly visually similar images becomes lower ranked.

2. Dominant Color Region based Indexing

[9] Dominant color region that is present in an image can be represented as a connected fragment of homogeneous color pixels which is observed by human vision. Image Indexing is dependent upon this notion of predominant color present in the display picture. The sectioned out dominant regions along with their additional features are used a a source of retrieving similar image from the data base. The image path, number of regions recognized, region information like normalized range, color and area of each particular region is stored in the file for future reference processing..

They are some drawbacks with the above mentioned approaches. Histogram approach is simple and easy but it does not allow for geometric information of images i.e. rotation and translation. In Dominant color region based indexing the main drawback is that it never retrieves the same objects of varying sizes as the similar image. For the smaller object the background will be the dominant region as shown in figure1.1, whereas in bigger object that object itself is dominant. Even though the semantics of the objects are same, they are not retrieved as similar images.

Fig 2.1. Images with different Foreground Object sizes

The proposed method can answer this problem because of considering only the foreground information and neglecting background details.

Dominant Color Identification of Foreground Objects

Dominant color identification of foreground objects retrieves more number of similar images based on foreground color irrespective of size and background color. The foreground information of the images are enough to identify the images properly. This is implemented by the proposed algorithm and by using some concepts like

1. Image Segmentation

2. Color Matching and Dominant Color Identification

3. Retrieval method

1. Image Segmentation

[10] Image segmentation is the motivation of this research work, and is used to distinguish this technique from previous works of image retrieval based on dominant color Identification. The color image is converted into the grayscale image and then using threshold method that will be converted into the binary image. In binary image the foreground is represented by maximum intensity value (1) and background is represented by minimum Intensity value (0). The binary image is converted into the color image by retaining the color values only in the foreground of the image.

2. Color Matching and Dominant Color Identification

The Segmented image is modified into smaller color set combination image. It involves mapping all pixels to their categories in color space. For each pixel in the image, a color is selected from smaller set of predefined colors which are very near to image pixel color and it will be stored as new color pixel in the image.

The dominant color of the foreground image is determined as the color response of each pixel in the modified image and stored in frequency table. The frequency table is sorted in descending order and then the first occurrence color will be the dominant color of the foreground of the respective image.

3. Retrieval Method

[10] The proposed technique Dominant color identification of foreground objects is used for all the color images that are present in the database. It is used to determine the foreground dominant color and then the extracted feature of dominant color and are stored. Whenever the query image is given by the user , the dominant color for foreground information is detected and retrived. This retrieval technique detects the database images whose foreground dominant color is similar to the foreground dominant color of query image. Those images are retrieved as the similar images for the query image.

A brief overview of the proposed project system architecture and design.

Fig1 : Depicts the architecture for the proposed system

From the above figure the proposed project is presented in an format in which it can de developed during the early research phase and also in system architecture phase.

System architecture.

We can divide the system architecture in to various algorithmic parts in order to implement the proposed system

1. Identify the query image

2. Gray scale image.

2.1. Convert the query image in to Gray scale image.

3. Finding the threshold value for the Gray scaled query image.

4. Finding the Background intensity on the query image.

5. Finding a binary value for the query image.

6. Find the dominant color.

Many of the above mentioned steps are implemented by using algorithms.

1. Identify the query image

Initially we need to consider a color query image for which we need to identify the search results. This image is loaded and then we retrieve relatively similar images from the database using various techniques that use dominant color identification of foreground object.

2. Gray scale image

In computing and photography, a gray scale digital image is an image in which the value of each pixel is a single sample carries only intensity information. Images of this sort, also known as black-and-white images and are composed exclusively of shades of gray, varying from black shade at the weakest intensity to white shade at the strongest.

The intensity of a pixel will be expressed within a given range between a minimum and a maximum, inclusive. This range is represented in a as a range from 0 (total absence, black) and 1 (total presence, white), with any fractional values in between.

2.1 Covert the query image in to Gray scale image.

Conversion of a color image to grayscale is not unique; different weighting of the color channels will represent the effect of shooting black-and-white film with various colored photographic filters on the cameras. A common strategy that will be used is to set the grayscale value of a pixel to the mean of its R,G, and B values.

To convert any color to a grayscale representation, first one must obtain the values of its red, green, and blue (RGB) primaries. Then find out the mean value of these primaries and assign them as the grayscale values of the image.

G=(R+G+B)/3

After completing the process a intensity histogram will be developed or constructed.

Gray scale algorithm.

Purpose: To convert the color image into a gray scale image and construct an intensity histogram

Input : CI, color image

Output : GI, grayscale image

IH, intensity histogram, an array of size 256

Method :

for each pixel in the color image,CI

{

find red value,Rci, of the pixel of CI

find green value,Gci, of the pixel of CI

find blue value,Bci, of the pixel of CI

intensity of the pixel of CI,Y=(R+G+B)/3

increment the value at index,Y, of IH

red value of the corresponding pixel of GI,Rgi=Y;

green value of the corresponding pixel of GI,Ggi=Y;

blue value of the corresponding pixel of GI,Bgi=Y;

}

3. Finding the threshold value for the Gray scaled query image.

This can be implemented by using Threshold value algorithm. In order to find the intensity threshold value based on which the image will be separated into foreground and background regions, we need to consider the output of gray scale image i.e. intensity histogram as a input in order to calculate the threshold vale.

Threshold Algorithm

Purpose: To find the intensity threshold value based on which the image will be separated into

foreground and background regions.

Input : IH, intensity histogram

Output : T, threshold value

Method :

i=least intensity

Nb value is calculated, the percentage of pixels with intensity,Y< i

Mb value iscalculated, the weighted mean of pixel intensities where Y<i

No value is calculated, the percentage of pixels with intensity,Y> i

Mo value is calculated, the weighted mean of pixel intensities where Y>i

4. Finding the Background intensity on the query image.

The background intensity can be achieved by using background algorithm. The gray scale image and the threshold will be taken as the inputs and the desired backgroung intensity is generated.

Background Algorithm

Purpose: To find the intensity that represents background

Input : GI, Grayscale image

T, Threshold

Output : BI, intensity that represents background

Method :

TLI=intensity value of top-left pixel of GI

TRI=intensity value of top-right pixel of GI

BLI=intensity value of bottom-left pixel of GI

BRI=intensity value of bottom-right pixel of GI

BI=(TLI+TRI+BLI+BRI)/4;

5. Finding a binary value for the query image.

Binary images are also called bi-level or two-level. This means that each pixel is stored as a single bit either 0 or 1. The names black-and-white, B&W, monochrome or monochromatic are used for this concept.

This can be achieved by binary algorithm, after forming the binary image. In order to produce a binary image the binary algorithm uses gray scale image, threshold and background intensity as an input. This image will be presented in black and white format. The white portion generally represents foreground and the black portion represents background.

Binary algorithm

Purpose: To form a binary image where the white portion represents foreground and black

portion represents background

Input : GI, Grayscale image

T, Threshold

BI, Background intensity

Output : BImg, Binary image

Method:

Each pixel value of the gray scale image, GI

We find intensity, Y value of the pixel

If the value of Y is less than T value and BI value is less than T value

Then Y=0 i.e. pixel belongs to background=1 then pixel belongs to foreground

If the value of BI is less than the T value then Y=1 pixel belongs to foreground.

Y=0 pixel belongs to background.

6. Find the dominant color.

Finally we will be able to find out the dominant color of the proposed system after passing through the various above mentioned stages.

Dominant color algorithm

Purpose: To find the dominant colour of the foreground of the image

Input : CI, color image

BImg, binary image

CLT, color look-up table

CRLT, color ratio look-up table

Output : DC, dominant color

Design

The design of the proposed system depicts the software in a number of different ways. First, the architecture of the system or product must be presented. Then, the various interfaces that connect the software to end-users or to other systems and devices. The software components that are used to construct the proposed system are initially designed. The design view of the proposed project may represent a different design or action, but finally the goal is to bound up to the set of basic design concepts that guide the later part of the proposed project i.e., coding and further implementation.

Scenarios

Various scenarios of the proposed system are given below. Every scenario which is listed below may result in a successful or a failure operation of the system. Every scenario will be dealt very carefully while developing the proposed system. The various scenarios are:

Adding an image to the database

Separating foreground of the image from its background.

Finding dominant color in the foreground of the image.

Deleting images from the database.

Retrieving Images from the database whose dominant color in the foreground object matches that of the query image supplied by the user.

1. Add Image

2. Delete Images

3. Retrieve Images

The description of each functional requirement is as follows:

Add Image

The user can add one image at a time to the database. If the image is not of a compatible format, then the system should report an error displaying that the image format is not supported. Also, all the compatible image formats should be displayed. There is no constraint on the size of the image. While adding image to the database, the category to which it belongs should be specified.

Delete Images

The user can delete any number of images at a time from the database. The user has to specify the category of images from which he is intended to delete some images. If there are no images under that category to be deleted, then the system should report an error displaying that no more images are available.

Retrieve Images

The user has to supply a query image to the system. If the query image is not of a compatible format, then the system should report an error displaying that the image format is not supported. Also, all the compatible image formats should be displayed. The user should also specify the image category from which he is intended to retrieve the images. Then, every image which is already in the database under that category and whose dominant color of its foreground object is almost similar to that of the query image is retrieved and displayed for the user.

Deliverables.

The results of a research review, gives the information about the latest technology and the image retrieval techniques that can be used to implement the proposed system.

Writing Services

Essay Writing
Service

Find out how the very best essay writing service can help you accomplish more and achieve higher marks today.

Assignment Writing Service

From complicated assignments to tricky tasks, our experts can tackle virtually any question thrown at them.

Dissertation Writing Service

A dissertation (also known as a thesis or research project) is probably the most important piece of work for any student! From full dissertations to individual chapters, we’re on hand to support you.

Coursework Writing Service

Our expert qualified writers can help you get your coursework right first time, every time.

Dissertation Proposal Service

The first step to completing a dissertation is to create a proposal that talks about what you wish to do. Our experts can design suitable methodologies - perfect to help you get started with a dissertation.

Report Writing
Service

Reports for any audience. Perfectly structured, professionally written, and tailored to suit your exact requirements.

Essay Skeleton Answer Service

If you’re just looking for some help to get started on an essay, our outline service provides you with a perfect essay plan.

Marking & Proofreading Service

Not sure if your work is hitting the mark? Struggling to get feedback from your lecturer? Our premium marking service was created just for you - get the feedback you deserve now.

Exam Revision
Service

Exams can be one of the most stressful experiences you’ll ever have! Revision is key, and we’re here to help. With custom created revision notes and exam answers, you’ll never feel underprepared again.