Search or add a thesis

Advanced Search (Beta)
Home > Classified Image Indexing for Content Based Retrieval

Classified Image Indexing for Content Based Retrieval

Thesis Info

Access Option

External Link

Author

Bashir, Muhammad Khawar

Program

PhD

Institute

University of Engineering and Technology

City

Lahore

Province

Punjab

Country

Pakistan

Thesis Completing Year

2019

Thesis Completion Status

Completed

Subject

Computer Science

Language

English

Link

http://prr.hec.gov.pk/jspui/bitstream/123456789/12138/1/Muhammad%20Khawar%20Bashir%20computer%20sci%202019%20uet%20lhr%20prr.pdf

Added

2021-02-17 19:49:13

Modified

2024-03-24 20:25:49

ARI ID

1676727714926

Similar


Increased availability of devices with camera and rapid growth and development of the internet has enlarged image databases for individuals and organizations. It has raised a need for an effective and efficient approach for searching, browsing and retrieving images from large image databases of different fields of life e.g. medicine, economics, education, architecture, etc. This problem is being addressed using Content-Based Image Retrieval (CBIR) by developing the number of algorithms that use different kind of features that includes both low and high level features. These features are used to measure the similarity between images. But these features extraction and similarity measure approaches have many limitations that resulted in excessive response time and retrieval accuracy. CBIR mainly depends on extracted features from image contents and if possible, with semantic concepts. So, the semantic gap needs to be narrowed down while extracting features that can help in increasing retrieval accuracy. To minimize the retrieval time, instead of comparing features, we can transform features into deep hash codes. Comparing numbers takes less time than text or features. So, we can reduce the retrieval time by comparing the deep hash codes of query and database images. We proposed changes in the objective function of Convolutional Auto encoder to extract features while triplet loss function in the last layer to convert features to binary hash code with semantic preservation and similar code for same types of extracted features. This approach reduces the dimensions of the features to binary hash code length that make retrieval easier and faster. Proposed image retrieval system has been tested with different data sets and comparisons have been made with different loss functions and hashing approaches. Experimental results indicate the effectiveness of the proposed approach and show improved retrieval accuracy.
Loading...

Similar Thesis

Showing 1 to 20 of 100 entries
TitleAuthorSupervisorDegreeInstitute
PhD
University of Engineering and Technology, Lahore, Pakistan
BCE
COMSATS University Islamabad, Islamabad, Pakistan
MSc
Quaid-i-Azam University, Islamabad, Pakistan
PhD
University of Engineering and Technology, Taxila, Pakistan
BCS
International Islamic University, Islamabad, Pakistan
University of Engineering and Technology, Lahore, Pakistan
PhD
International Islamic University, Islamabad, Pakistan
PhD
University of Engineering and Technology, Lahore, Pakistan
BS
International Islamic University, Islamabad, Pakistan
BS
International Islamic University, Islamabad, Pakistan
MSc
Quaid-i-Azam University, Islamabad, Pakistan
BCS
International Islamic University, Islamabad, Pakistan
University of Engineering and Technology, Lahore, Pakistan
MSc
Quaid-i-Azam University, Islamabad, Pakistan
PhD
Iqra University, Islamabad, Pakistan
University of Engineering and Technology, Lahore, Pakistan
PhD
National University of Computer and Emerging Sciences, Islamabad, Pakistan
MA
International Islamic University, Islamabad, Pakistan
PhD
University of Engineering and Technology, Taxila, Pakistan
MS
International Islamic University, Islamabad, Pakistan
TitleAuthorSupervisorDegreeInstitute
Showing 1 to 20 of 100 entries

Similar Books

Loading...

Similar Chapters

Loading...

Similar News

Loading...

Similar Articles

Loading...

Similar Article Headings

Loading...

سبز بستیوں کے غزال

سبز بستیوں کے غزال

                سانجھ پبلی کیشنز سے 2018ء میں چھپنے والا ناطق کی غزلیات کا ایک مجموعہ سر بستیوں کے غزال بھی ہے۔اس کتاب کا انتساب شمس الرحمان فاروقی کے نام ہے اس میں کل 54غزلیں شامل ہیں۔اس میں انہوں نے پنجاب کی سرزمیں ،کھیت کھلیان ،پھل پھول،ہریالی یہاں تک کہ پنجاب میں جڑے رشتے ،اسی مٹی سے اٹھنے والی خوشبو اور اس سر زمین کے لیے جان دے دینے والے رشتوں کو اردو غزل میں شاعری کے ذریعے پروان چڑھایا ہے۔

                علی اکبر ناطق نے اپنی تمام تر تحریری جمالیات  کے ساتھ پنجاب کی خوبصورتی کو عیاں کرکے ایک نئی مثال قائم کی ہے۔ان کی شاعری میں کچھ ایسے الفاظ کا بھی استعمال کیا گیا ہے جو کہ پنجابی کے ہیں یوں تو بہت سے شاعر حضرات ایسے ہیں جو اپنی شاعری میں پنجابی کے الفاظ استعمال کرتے ہیں۔لیکن ناطق نے اردو غزل میں الفاظ کا اصل اور بالکل منفرد طریقے سے  تخلیقی استعمال کیا ہے۔شمس الرحمٰن لکھتے  ہیں:

’’ناطق کی غزل اپنے قصے کی دیواروں اور کھیتوں کی سبز مٹی سے جڑی ہے اس کی زبان کا خمیر اپنی دھرتی کی خوشبوؤں سے اٹھا ہے۔اس کا ایک ایک مصرع اس کے اٹوٹ  سمبندھ کی گواہی دیتا ہے۔یہ ہنر آفر ین شعری طلسم کسی کاوش کا نتیجہ نہیں بلکہ وہ الہامی  اور وجدانی  توفیق کی جزا ہے جس میں ناطق کو اپنی شاداب و خوشی  رنگ پائینوں والی دھرتی سے باندھے رکھا ہے۔‘‘(8)

                ناطق کی شاعری میں جس طرح منظر نگاری سے کام لیا جاتاہے۔قاری کو محسوس ہوتا ہے کہ جیسے نقش بولتے ہیں۔ان منظروں میں وہ سماں ہوتا ہے کہ جیسے تاریخ خود اپنی وضاحت کررہی ہو۔ حال میں ہونے والے اور مستقبل...

Epidemiology of Squamous Cell Carcinoma in Response to Different Hazardous Chewing Causes in Lahore, Pakistan-a Unicenter study epidemiology of oral carcinoma in Lahore, Pakistan

Oral squamous cell carcinoma (OSCC)being the world’s most prevailing and frightening cancerous disorder lacks the sufficient data in Pakistan despite of its higher magnitude and prevalence. Objective: This study was specifically designed and conducted with the aim to identify the frequency of this disorder along with causative factors in past three years in a tertiary care hospital of Lahore, Pakistan. Methods: Epidemiological study was conducted using retrospective randomized method and all pre-requisites were filled. The clinical profiles of patients were collected from Maxillofacial and Oral Surgery Departmentof Pathology, Mayo Hospital Lahore. Patients who had undergone treatment for OSCC were contacted and interviewed for information about demographic regions, previous history of malignancy, disease onset, chewing habits, exposure to pesticides, industrial exposure to metals etc. And all particulars were not and compiled on questionnaire. Results: A total of 54 patients from different districts of Punjab participated in the study. Percentages for each possible causative chewing habit were calculated and 87.50 % of population was found addicted to different habits. Genetic factor might have contributed in remaining for development of OSCC. Conclusions: Informative data provided in this study will be helpful to be used by the government and private health agencies while designing and planning management of oral health problems and allocating health budgets in focusing this issue

Wellbeing of Working Children in Carpet Industry in Punjab, Pakistan: Issues, Causes and Interventions

Child labor is perceived to be a severe problem as it is supposed to be destructive not only for intellectual and physical development of children but also for their life as a whole or their wellbeing especially that of young children. The danger is intensified for those children who work in hazardous industries like carpet industry. A child works for a variety of reasons, the most important being poverty and the induced pressure upon his/her to escape from this plight. The prime objective of the present research was to identify the factors contributing to child labor and effects of work-related issues on the wellbeing of carpet weavers. A cross sectional survey was conducted in three districts of Punjab i.e. Faisalabad, Sheikhupura and Toba Tek Singh selected where a sizable number of child carpet weavers were found by using the secondary data sources. A sample of 320 carpet child workers of age group 8-17 years from each locality and villages were selected randomly using the list of carpet household. Both quantitative and qualitative methods were used in order to get detailed information about the issue under study. For the quantitative approach, the information was collected through a well-structured questionnaire consisting of both closed ended and open ended questions. For qualitative approach, to get the detailed information about complex phenomenon of child labor focus group discussions with the parents and contractors were conducted. Descriptive statistics such as frequency distribution mean and standard deviation and inferential statistics such as chi-square, Gamma tests and regression analysis were applied to analyze the data for exploring the research objectives and hypotheses. The key findings of the descriptive analysis show that the majority of the respondent belong to the labor class, had a large family size, low family income and the main cause for not attending school and doing the value laden activity of carpet weaving was poverty. A huge majority 92 percent reported that they were assisting their parents in family income and that they cannot afford to go to school. The bi-variate analysis demonstrate that significant relationship between all socioeconomic factors and wok-related issues (i.e. age, monthly income, parent’s education, working hours, workplace conditions, employer’s behavior, child abuse and hazards) and the personal wellbeing of carpet working children. The multi-variate analysis results reveal that the most important and contributing socio-economic factors in explaining the satisfaction level of personal wellbeing of respondents were; monthly income, father’s education, parental health problem, and economic involvement of family members. It also emerged from the multivariate analysis that work-related issues like poor working conditions, long working hours, employer’s behavior child abuse and work-related 18 hazards also affect the personal wellbeing of respondents. From the focus groups discussions with parents it was found that the major cause of children’s involvement in hazardous work like carpet weaving was the parent’s inability to provide even basic needs to their family so they are forced to send their children to work instead of school. It is evident from the discussion that the parents are aware of the short and long term health impact like musculoskeletal disorders, respiratory disorders, injuries, eyesight problems, nerve disorders, skin problems of this work. It is suggested that a comprehensive strategy consisting of macro as well as micro policies has to be commenced to resolve the problem. In this context, different measures are suggested to control, reduce and eradicate the participation of children in the carpet weaving industry.