Search or add a thesis

Advanced Search (Beta)
Home > Intelligent Gender Identification Using Diverse Facial Features in Different Conditions

Intelligent Gender Identification Using Diverse Facial Features in Different Conditions

Thesis Info

Access Option

External Link

Author

Haider, Khurram Zeeshan

Program

PhD

Institute

University of Engineering and Technology

City

Taxila

Province

Punjab

Country

Pakistan

Thesis Completing Year

2018

Thesis Completion Status

Completed

Subject

Computer Science

Language

English

Link

http://prr.hec.gov.pk/jspui/bitstream/123456789/10092/1/Khurram%20Zeeshan%20Haider_Comp%20Engg_2018_UET%28T%29_PRR.pdf

Added

2021-02-17 19:49:13

Modified

2024-03-24 20:25:49

ARI ID

1676727778631

Asian Research Index Whatsapp Chanel
Asian Research Index Whatsapp Chanel

Join our Whatsapp Channel to get regular updates.

Similar


Humans can effortlessly determine the gender of other person. This has stimulated interest to enable computer machine of accurate guessing the human faces as male or female. Major problems in face classification are due to the large variance in appearance in a digital image when it is captured / exposed to different lightning and unfamiliar pose. Gender classification has an extensive usage in numerous problems and domains. Automated gender classification is an area of great significance and has huge impact and potential for future research. Its use is significant in several industrial applications such as monitoring, security, surveillance, biometrics, commercial profiling and human computer interaction. Gender has been identified using different traits like gait, iris and hand shape but a major and significant work has been carried out based on face. Main emphasis of this research work is critical assessment of different methods used in Gender Classification and highlighting favorable and unfavorable factors of these existing techniques. In next sections methodologies have been presented for efficient gender classification in still images and animated videos and over smart phones. Schemes have been presented for these diverse medium of digital image processing. We have conducted experiments to identify gender for the comparisons purpose for both areas of focus i.e. consumer face images captured run-time and fictional characters in animated movies. Flow of work, implementation of proposed classification methodology and learning algorithm is part of this thesis. Main modules of Gender Classification task are image acquisition, face detection, image normalization, feature extraction and classification. Every task has been thoroughly iii investigated with state of art methods and then final modeling is proposed, implemented and tested.
Loading...
Loading...

Similar Books

Loading...

Similar Chapters

Loading...

Similar News

Loading...

Similar Articles

Loading...

Similar Article Headings

Loading...

لسان فسوں

لسان فسوں
فلک کی جالیوں سے لگ کر رونے والی۔۔۔!
میری رگوں میں خون بن کر دوڑتی رہتی ہے
میں زمین پر۔۔۔اسی کے خال و خد بناتے ہوئے!
دستِ حنائی کے لمس۔۔۔!
دلفریب لہجے کے سحر میں ڈوبے ہوئے۔۔۔!
تلمیحاتِ خمسہ کی ساری روایتیں۔۔۔!
غیلان،عِلاف،کندی۔۔۔!
فرزند سینا اور فارابی کی آیتیں بھی جانتا ہوں
طلوع سحر کا رازی۔۔۔جب اک وعدہ شام ہونے لگتا ہے
پھر میں موسم زلیخا کا۔۔۔
اک خوب صورت بہانہ بننے لگتا ہوں
سرخ سبز پرندوں کا ورد زباں ہونے لگتا ہوں

جب بھی فسوں ساز شاموں کی بات ہوتی ہے
زیتون و صندل۔۔۔!
سفید کبوتروں جیسے صحیفے پڑھنے لگتی ہیں
شاخوں پر پھول پتے نازل ہونے لگتے ہیں
جنوں کی روشنی میں جناب عنترہ اور عبلہ سے بھی ملاقات ہوتی ہے
جب طاق لمحے۔۔۔مجھ سے گلے ملتے ہوئے گزرتے ہیں
پھر تخلیقات عشق کا سنہری زمانہ بننے لگتا ہوں
سرخ سبز پرندوں کا ورد زباں ہونے لگتا ہوں

لسان فسوں جب دشت میں!
گلابی صحیفوں سے آیتیں تلاوت کرنے لگتی ہے
نشاط تعبیر کی وادیوں میں خوشبو۔۔۔!
شاداب جزیرں میں چاندنی رقص کرنے لگتی ہے
دل دھڑکنے لگتے ہیں
بزرگ جوگیوں سے۔۔۔!
چنبیلی کے سائے میں مناظرہ کرنے لگتے ہیں
لذت زخم کی تفسیر کرتے ہوئے!
جب سیفو،عبلہ اور ماریہ قندیل روشن کرتی ہیں
پھر قلندرانہ رقص کرتے ہوئے۔۔۔میں پروانہ بننے لگتا ہوں
سوسن و نسترن کی قسم!
میں لذت خمار کا تعارف غائبانہ بننے لگتا ہوں
سرخ سبز پرندوں کا ورد زباں ہونے لگتا ہوں

Analysis of Rights of Foetus in the Light of Searah Nabviyah: Comparative Study With Positive Law

The article titled: the rights of foetus in Islamic law, aims at explaining the rights of foetus without discussing different theories of the scholars in this regards. It also defines the foetus and gives literal and technical meanings besides different stages of foetus mentioned in the Holy Quran and the Hadith. The article explains the rights granted to foetus in the lights of serah before birth and these rights are a binding on the concerned people and violation of foetus’ s rights is prohibited and it is a cognizable offence. The article also discusses the attitude of west regarding foetus rights as the western society is totally ignorant about the rights of foetus and their legislation in this regard is contrary and several western laws are causing the violation of foetus’s rights. Thus, the champions of human’s rights are blind to the rights of foetus which is foundation and beginning of human life and first step for the human race. It is that has given these rights to mankind for the first time and informed human being about their rights through the first human’s rights charter given at the time of the Noble Prophet {blessing of Allah and peace be upon him}. This charter is known as the charter of Madina between the Muslims and the Jews. The article concludes: mankind cannot be protected unless the sperm of man is protected and foetus is protected in the womb of the mother from abortion because these are the future of humanity.

An Ocr System for Printed Nastaliq Script: A Segmentation Based Approach

Machine simulation of human reading has been a subject of intensive research for almost four decades. The latest improvements in recognition methods and systems for Latin script are very promising and matured product are available for those languages in the market. On the contrary, despite more than one decade of research in the field of Urdu Optical Character Recognition (OCR), the reading skill of the computer is still way behind that of human. Automatic Urdu character recognition is a challenging task due to less attention of researchers and intrinsic complexity of Urdu text. That is highly cursive and calligraphic nature, diagonality in writing, and vertical overlap between characters in a sub-word. In this research, we present a novel implicit segmentation based technique for development of an OCR for printed Nasta''liq text lines. This work introduces a novel and robust approach based on statistical models that provide solution for recognition of Nasta’liq style Urdu text. Unlike to classical approaches which segment text into words, ligatures or characters, we employ an implicit segmentation where text lines are recognized during segmentation. The developed system is evaluated on standard Urdu text databases and compared with the state-of-the-art recognition techniques proposed till date. In the proposed recognition system, we use two strategies, first is based on manual features and second on automatic features. In the first strategy, we split each text line image into small frames of width ‘n’ by using a sliding window and extract many features from each frame. These features are then concatenated to form a feature vector for the text line. In the second strategy, we extract features automatically by using the Multi-dimensional (MD) Long Short Term Memory (LSTM) model in one scenario and by Convolutional Neural Network (CNN) model in other scenario. Features extracted from the text lines along with their respective transcriptions are fed to a Recurrent Neural Network (RNN) for training or classification. Recognition is obtained by using MDLSTM based recognizers with the Connectionist Temporal Classification (CTC) output layer. The experiments conducted on a standard UPTI database yield promising results. We obtained 96.40% (3.6% error rate) recognition rates using manual features, 98% (2.0% error rate) using raw pixels based features and 98.12% (1.88% error rate) using CNN based features.