A Various Approaches and Literature Based on CBIR: A Survey: [Essay Example], 1457 words GradesFixer

Haven't found the right essay?

Get an expert to write your essay!


Professional writers and researchers


Sources and citation are provided


3 hour delivery

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

A Various Approaches and Literature Based on CBIR: A Survey

Print Download now

Pssst… we can write an original essay just for you.

Any subject. Any type of essay.

We’ll even meet a 3-hour deadline.

Get your price

121 writers online

Download PDF


A. Query Techniques

Query via illustration is a query manner that includes providing the CBIR procedure with an example image that it’ll then base its search upon.

B. Semantic Retrieval

The perfect CBIR process from a personal perspective would contain what’s known as semantic retrieval, the place the user makes a request like “to find pictures of Abraham Lincoln”. This sort of openended assignment is very complex for desktops to perform pictures of excellent Danes seem very distinctive and Lincoln may not always be dealing with the digital camera or in the identical pose.

C. Content Comparison using distance measure

The most widely recognized process for assessing two pictures in CBIR is using a picture separate measure. A picture removes measure analyzes the likeness of two pictures in different measurements comparing to hues, surface, shape and, others.

D. Common features for image retrieval

A function is outlined as capturing a particular visual property of an image. Regularly, image features can be both world and regional. The global aspects describe the visible content material of the complete image, whereas local features describe the areas or objects (i.e. a little gathering of pixels) of the picture content. The capability of worldwide extraction is that it is rapid for both extricating feature and registering closeness. Be that as it may, worldwide featureis regularly excessively unbending, making it impossible to speak to a picture. In particular, they can be oversensitive to the area and thus neglect to distinguish vital visual attributes. Local-feature approaches give a somewhat preferred recovery adequacy over worldwide elements. They speak to images with different focuses in a component space as opposed to single point worldwide element representations. While local methodologies give more robust data, they are more costly computationally because of the high dimensionality of their component spaces and more often than not require closest neighbors guess to perform focuses coordinating. A few important features that can be utilized as a part of IR will be clarified in the following subsections.

  1. Color Features
  2. The color has broadly been utilized as a part of IR systems, as a result of its simple and quick calculation. Color is additionally a natural element and assumes an essential part in image matching. Most IR frameworks utilize colorspace, histogram, minutes, color soundness vector, and winning color descriptor speak to color. The color histogram is a champion among the most regularly usedcolor highlight representation in IR. The first thought to utilize histogram for retrieval comes from Swain and Ballard, who understood the ability to distinguish an item utilizing color is much bigger than that of a gray scale. Despite the fact that the worldwide color feature is easy to compute and can give sensible discriminating power in IR. It tends to give an excess of false positives when the image accumulation is huge. Numerous research results recommended that utilizing color design is a superior answer for IR. To extend the worldwide color feature to a local one, a characteristic methodology is to isolate the whole image into sub-blocks and extract color features from each of the sub-blocks. The advantage of this methodology is its precision while the disadvantage is the general troublesome issue of reliable image segmentation.

  3. Texture Features
  4. Texture is anasset that addresses the surface and structure of a picture. Texture can be characterized as a normal redundancy of a component or example on a surface. Image textures are complex visual examples made out of substances or areas with sub-designs with the characteristics of brightness, color, shape, size, etc. The commonly used texture descriptors are Wavelet Transform, Gabor-filter, and Tamura features.

  5. Shape Features
  6. Shape can by and large be characterized as the depiction of a question paying little mind to its position, introduction, and size. Along these lines, shape highlights ought to be invariant to interpretation, turn, and scale for a successful IR. In the direction of using shape as an image feature, it is necessary to determine object or region boundaries in the image and this is a challenge. Contrasted and color and texture features, shape components are normally portrayed after images have been sectioned into areas or articles. Since robust and accurate image segmentation is hard to accomplish, the utilization of shape components for IR has been constrained to extraordinary applications where things or zones are promptly accessible. As a rule, the shape portrayals can be separated into two classifications, limit based those utilizations just the external limit of the shape and area based that uses the whole shape district. The best delegates for these two classes are Fourier descriptor and minute invariants.

  7. Spatial Location Features
  8. Spatial location is likewise critical and is utilized for locale segmentation. Spatial location is portrayed as top/bottom, left/right and back/front according to the position of an object in an image. For instance, the ocean and sky might have the same qualities of texture and color however the spatial data is not comparable. Sky normally speaks to the above portion though the sea is at the beneath bit of an image. Thus, the spatial information of different items in an image extracts huge data for retrieval of images. Most spatial information is displayed in terms of2D strings. The 2D string spatial quadtree is utilized for spatial information representation.

  9. Local Image Features
  10. Local features are small square, sub-images extricated from the first image. They can be considered having two different sorts:

    The patches: They are separated from the images at salient points and dimensionality diminished utilizing Principal Component Analysis (PCA) transformation.

SIFT descriptors: They are removed at Harris interest focus. To utilize local features for IR, three different techniques are accessible.

i) Direct transfer: The local features extricated from every database image and from the query image. At that point, the closest neighbors for each of the local features of the query searched and the database images containing the greater part of these neighborsare returned.

ii) Local feature image distortion model (LFIDM): The nearby highlights from the question picture appeared differently in relation to the neighborhood highlights of each picture of the database and the divisions between them are summed up. The pictures with the most decreased total partitions are returned.

iii) Histograms of local features: A moderately large amount of local points from the database is clustered after which each and every database image represented by utilizing a histogram of lists of those groups. These histograms are then when thought about utilizing the Jeffrey divergence [10].


CBIR applications are as follows:

  • Crime prevention:The police forces use automatic face recognition systems.
  • Security Check: Fingerprint or retina scanning for access privileges.
  • Medical Diagnosis:To aid diagnosis by analyzing identical past caseswith the help of CBIR in a medical database of medical images.
  • Intellectual Property:The candidate mark is correlated with prevailing marks to assure no risk of confusing property ownership with trademark image registration [11].


ShantanuMisale, et al. [2018] This paper gives the integrated the advantages of both LTrP and BoW. Initially, interest pointsare detected using the speed up robust feature (SURF) and further local features (using LTrP) are extracted from local patch around each interest point. After feature extraction, BoWis used to obtain the global representation of an image. Further, artificial neural network (ANN) is used for index matching and image retrieval task. Performance evaluation of theproposed system has been carried out using average retrieval precision (ARP), average retrieval recall (APR) and F-score on two state-of-the-art databases viz. Caltech256 and GHIM10K. Performance of the proposed system is compared with the existing feature descriptor and CBIR systems. Performance analysis shows that the proposed system outperforms the existing methods and traditional CBIR framework i.e. use of similarity measurement [12].

SafaHamreras, et al. [2018] This paper propose a structure for “Calculation Selection” for CBIR. The system depends on the model of RICE and is adjusted to fulfill a given inquiry relying upon its attributes by picking the best traditional CBIR-Algorithm from an Algorithm-Portfolio. Upwards of six calculations for content based picture recovery have been incorporated into the system as options for the distinctive questions, including the preparation step. These calculations extend from RGB color minutes, RGB shading histogram to the local binary pattern (LBP), and so on.Therefore, there has been put an effort in the framework to cover the basic characteristics of images i.e. Color and texture. Also, the framework integrates two color models to better enhance the Algorithm-Query adaptation process [13].

AtifNazir, et al. [2018]This paper proposed a new CBIR technique to fuse color and texture features. Color Histogram (CH) is used to extract color information. Texture features are extracted by Discrete Wavelet Transform (DWT) and Edge Histogram Descriptor (EDH). The features arecreated for each image and stored as a feature vector in the database. The work is evaluated using Corel l-k dataset. To examine the accuracy of the other proposed systems, precision and recall methods are used that provides the competitive and efficient result. The test outcomes demonstrate that our proposed technique outflanks with existing CBIR systems [14].

Remember: This is just a sample from a fellow student.

Your time is important. Let us write you an essay from scratch

100% plagiarism free

Sources and citations are provided

Cite this Essay

To export a reference to this article please select a referencing style below:

GradesFixer. (2019, April, 10) A Various Approaches and Literature Based on CBIR: A Survey. Retrived January 19, 2020, from https://gradesfixer.com/free-essay-examples/a-various-approaches-and-literature-based-on-cbir-a-survey/
"A Various Approaches and Literature Based on CBIR: A Survey." GradesFixer, 10 Apr. 2019, https://gradesfixer.com/free-essay-examples/a-various-approaches-and-literature-based-on-cbir-a-survey/. Accessed 19 January 2020.
GradesFixer. 2019. A Various Approaches and Literature Based on CBIR: A Survey., viewed 19 January 2020, <https://gradesfixer.com/free-essay-examples/a-various-approaches-and-literature-based-on-cbir-a-survey/>
GradesFixer. A Various Approaches and Literature Based on CBIR: A Survey. [Internet]. April 2019. [Accessed January 19, 2020]. Available from: https://gradesfixer.com/free-essay-examples/a-various-approaches-and-literature-based-on-cbir-a-survey/

Sorry, copying is not allowed on our website. If you’d like this or any other sample, we’ll happily email it to you.

By clicking “Send”, you agree to our Terms of service and Privacy statement. We will occasionally send you account related emails.



Your essay sample has been sent.

Want us to write one just for you? We can custom edit this essay into an original, 100% plagiarism free essay.

thanks-icon Order now

Hi there!

Are you interested in getting a customized paper?

Check it out!
Having trouble finding the perfect essay? We’ve got you covered. Hire a writer

GradesFixer.com uses cookies. By continuing we’ll assume you board with our cookie policy.