Search or add a thesis

Advanced Search (Beta)
Home > An Intelligent Sparse Visual Feature Descriptors for Content-Based Image Retrieval

An Intelligent Sparse Visual Feature Descriptors for Content-Based Image Retrieval

Thesis Info

Access Option

External Link

Author

Mehmood, Zahid

Program

PhD

Institute

University of Engineering and Technology

City

Taxila

Province

Punjab

Country

Pakistan

Thesis Completing Year

2017

Thesis Completion Status

Completed

Subject

Applied Sciences

Language

English

Link

http://prr.hec.gov.pk/jspui/bitstream/123456789/8400/1/Zahid_Mehmood_Computer_Engineering_2017_UET_Taxila_HSR_15.06.2017.pdf

Added

2021-02-17 19:49:13

Modified

2024-03-24 20:25:49

ARI ID

1676725471568

Asian Research Index Whatsapp Chanel
Asian Research Index Whatsapp Chanel

Join our Whatsapp Channel to get regular updates.

Similar


Content-based image retrieval (CBIR) techniques are used to retrieve similar images from image repositories by utilizing the visual contents of the images. From last few years, bagof- visual-words (BoVW) model is most commonly used for image retrieval and got promising results in terms of accuracy and effectiveness. However, BoVW model still has some problems, such as an image is represented as an orderless global histogram of visual words that neglects the spatial layout of the image. Spatial information is an important component that provides discriminating details for accurate retrieval of images. In this thesis, three novel approaches for image representations are presented by the selection of appropriate semantic regions of an image by constructing histograms of visual words. The standard image databases are used to determine the efficiency of proposed approaches. Following approaches are presented in this dissertation: A novel image representation is presented using the characteristics of local and global information in the form of histograms of visual words. The global information is obtained by constructing the histogram of visual words over the whole image, while the histogram of visual words for local information is constructed over the local rectangular region of the image. The local histogram represents the spatial information of salient objects. In order to verify the performance of the proposed approach, a number of experiments are conducted on the standard image databases (Corel-A, Caltech-256, and Ground truth). The results show that the proposed image representation significantly enhance the effectiveness of image retrieval. Based on the semantic similarity in an image, another image representation is proposed by constructing the histograms of visual words by splitting an image into two rectangular regions that add the spatial information to the inverted index of the BoVW based image representation. By utilizing this phenomenon of image representation, different visual words for upper and lower rectangular regions of an image are obtained for better image retrieval performance. For the verification of proposed approach, extensive experiments are conducted vii on Corel-A, and Ground truth image databases, proof the robustness of the proposed approach. In order to overcome the problems of overfitting on large dictionary sizes, lack of spatial information, and to reduce the computational cost, a new image representation based on the weighted average of triangular histograms (WATH) is also introduced. The image is divided into four triangular regions in order to incorporate the spatial information to the inverted index of the BoVW based image representation, and a histogram of visual words are computed from each triangular region. An appropriate weight is assigned to each histogram in order to eliminate the aforementioned problems. The assigned weight reduces; the size of the dictionary by reducing the non-salient visual words, and the computational cost. The proposed approach also provide the consistent performance on large dictionary sizes. The quantitative and qualitative analysis conducted on two image databases (Corel-A and Corel- 1500) shows the robustness of the proposed approach among the recent image retrieval approaches. Keywords: Content-based image retrieval (CBIR); Bag-of-visual-words (BoVW); Local and global histograms; Rectangular spatial histograms; Weighted triangular histograms.
Loading...
Loading...

Similar Books

Loading...

Similar Chapters

Loading...

Similar News

Loading...

Similar Articles

Loading...

Similar Article Headings

Loading...

مولانا عبدالعزیز

مولانا عبدالعزیز گوجرانوالہ
دو ماہ ہوئے کہ مولانا عبدالعزیز صاحب خطیب و امام جامع مسجد گوجرانوالہ نے جو دیوبند کے عالم اور وقت کے بڑے محدث تھے، وفات پائی، انہوں نے محاح و مسانید کی مختلف کتابوں کی فہرستیں بطور اطراف بڑی محنت سے لکھی تھیں، جن میں صرف بخاری کی فہرست نبراس الساری فی اطراف البخاری کے نام سے چھپی ہے، مرحوم نے مجھے لکھا تھا کہ مسند ابن حنبل کی بھی ایک فہرست بنائی ہے، اور وہ اس کے چھپوانے کی فکر میں تھے، کیا اچھا ہو اگر ان کی یادگار میں ان کی یہ کتاب گوجرانوالہ کے قدرداں چھپوا سکیں، یاوہ اس نسخہ کو کسی قدر شناس کے سپرد کریں، کہ وہ اس کو چھپوا کر اس فیض کو عام کرے۔ (سید سلیمان ندوی، دسمبر ۱۹۴۰ء)

 

المصادر في القراءات القرآنية بين النصب والرفع

 In Arabic language the source from which all nouns and verbs are derived is called  (المصدر). Verbal noun (Al-Masdar:  (المصدر  is a very important derivative in Arabic. It is a noun derived from the verb to refer to the action or activity implied in the verb, e. G.  ((كتابة   “writing” as a process- derived from the verb (كتب) to  “write”. A verbal noun represents a change in the form of a verb which allows it to be used as a noun in a sentence. Verbal noun is a type of noun which can bear the article (ال) or tanwin   (تنوين ) and can be declined according to the sentence i.e. Nominative, accusative and genitive case. This article deals with the verbal nouns in the Holy Quran that appeared once in the nominative case and in other Qiraat it was read as accusative case. For e.g. (Al-Hamd) is read as nominative and accusative form. الرفع على قراءة حفص: ( الحمدُ لله رب العالمين ) و فى قراءة أخرى : ( الحمدَ لله رب العالمين ) Likewise other examples are: (سورةٌ أنزلناها )- (سورةً أنزلناها) (سلامٌ عليك)- (سلامًا عليك) Similarly : النصب على قراءة حفص: ( و بالوالدين إحسانًا) و فى قراءة أخرى : ( و بالوالدين إحسانٌ) Thus, the article highlights the semantic treasures embedded in the Qiraat of the Holy-Quran.

Development and Validation of Module in English at Secondary Level in Pakistan

The study was conducted to “Develop and Validate Module in English at Secondary level in Pakistan”. Therefore, the researcher developed a Module consisting of six units on the first five lessons of the textbook of 9 th class. The components of this module were Title, Introduction, Pre-requisite knowledge, Method of study, General objectives, Specific Objectives, Content (Input), Learning activities, Pre-test, Post-test and Feedback. The contents of the module were taken from the first five lessons of the English textbook of class IX. The basic language skills were focused for designing the activities and self-assessment tests of the units. “Introduction" was given at the start of each unit of the module to motivate and brief the students about the task they had to do. General objectives were given at the start of a module and specific objectives were placed at the beginning of each unit of the module. The main objectives of the study were: (a) To develop a sample module from the textbook of English for the 9 th class. (b) To validate a module determining their effectiveness by teaching in the classroom. (c) To validate module determining their effectiveness from the performance of low and high achievers in the classroom. The module was validated by conducting lessons in the classroom with its help. Therefore, the Pre-test Posttest were used as the instruments of the study. The Pre-test was used to find out the competencies of the students to deal with the material presented in the module. The validation of the module was checked by administering the same pre- test as a post-test to the subjects of both experimental and control groups by changing the arrangement of the items on the pattern of “Even Odd Numbers”. The module consisting ivof six units were taught in 14 weeks and it consumed 80 hours of the students for solving the activities given at the end of the module. The students of secondary classes studying in Government public secondary schools were the population of study. The control group as well as the experimental group was of equal size, each having 30 students of 9th class. The scores of pre-test and post-test were the data of study. The significance of difference between the scores of groups at 0.05 levels was tested by applying t-test and analysis of variance. The study proved that the material designed as a module promoted independent learning habits in the learner, provided opportunity to proceed at his own pace, ensured active participation, useful for slow as well as of bright students, enabled the students to comprehend difficult concepts, and kept them on the track. For this purpose, it was recommended that the policy makers should take steps for the development and validation of modules at secondary school level and the teacher training institutions should take steps for the training of the teachers for the development and validation of modules in different subjects. Textbook board may arrange workshops for writing of the books on modular pattern and the school libraries should be enriched with the books on the topics of development and validation of modules. The subject specialists and senior teachers should be trained to revise and update the modules in the light of modern researches on continuous basis. In spite of the fact that the material developed as a module under this study proved valid as a result of better performance of the students in the experimental group. However, there is also need of further studies on this topic by controlling some other variables such as attitude of the students, level of intelligence, timing of work that may influence the performance of the students.