Search or add a thesis

Advanced Search (Beta)
Home > Improved Face Recognition Using Image Resolution Reduction and Optimization of Feature Vector

Improved Face Recognition Using Image Resolution Reduction and Optimization of Feature Vector

Thesis Info

Access Option

External Link

Author

Muhammad Almas Anjum

Program

PhD

Institute

National University of Sciences & Technology

City

Islamabad

Province

Islamabad

Country

Pakistan

Thesis Completing Year

2008

Thesis Completion Status

Completed

Subject

Computer Science

Language

English

Link

http://prr.hec.gov.pk/jspui/handle/123456789/442

Added

2021-02-17 19:49:13

Modified

2024-03-24 20:25:49

ARI ID

1676727773564

Similar


Face recognition is a difficult problem that involves automated matching of a given face image with corresponding person’s image(s) in a database. Face recognition finds application in areas like surveillance & security, digital libraries and human computer interactions. Successful, speedy and practically feasible face recognition method depends heavily on the choice of feature vector used for classification and addressing the curse of image dimension. The dimension reduction and the skill to acquire minimum size of feature vector required for face recognition for diverse facial expressions is a challenging task in face recognition. Dimension reduction results in removal of irrelevant variables alongwith noise therein and a lower computation complexity of subsequent processing. This dissertation addresses the challenges of dimension reduction, choice of minimum size feature vector for face recognition and minimization of adverse effects of varying facial expressions on the recognition through reduction in image resolution. In preprocessing of face images, scale normalization is carried out through a novel scale normalization algorithm to retain only the facial part of images. This helps in reducing computational complexity by restricting dimensions of image to face region only. Tilt of face images is removed by calculating the gradient between the two eyes and applying the reverse rotation. The issue of dimensionality is addressed first by gradually reducing image resolution through spatial domain low pass filtering followed by decimation. The second method involves novel coefficient selection strategies to choose the minimum dimension of feature vector required for recognition with maximum recognition rate and reduced computational complexity. Face images with varying image resolution are obtained by varying the decimation factor. The effects of variation in image resolution on face recognition have been evaluated using template matching and Principle Components Analysis (PCA) based face recognition techniques. Classical PCA technique has been modified into sub-holistic PCA. Better recognition rate is achieved using modified PCA method with reduced image resolution. Improved recognition rate results are reported using novel coefficients selection and optimization methods in Discrete Fourier Transform (DFT), Discrete Cosine Transform (DCT) and Discrete wavelets Transform (DWT) based face recognition methods. The experiments are carried out for various image resolutions using five different datasets. Improved recognition rate of 97.2% (template matching), 87% (PCA), 94% (Sub-holistic PCA), 100% (DFT), 95.75% (DCT) and 99.25% (DWT) is achieved at a specific image resolution for different datasets. The resolution reduction method used with square images is then extended to hexagonal images. A new technique based on Diagonal grow and Butterfly structure methodology has been developed for sampling and indexing hexagonal structure in hexagonal image processing frame work. Proposed strategy offer less pixel redundancy as compared to existing techniques. Reduction in pixel redundancy varies according to size of square image.
Loading...
Loading...

Similar Books

Loading...

Similar Chapters

Loading...

Similar News

Loading...

Similar Articles

Loading...

Similar Article Headings

Loading...

یہ محبت اور شفقت آپؐ کی

یہ محبت اور شفقت آپؐ کی
ہم تو چاہیں صرف نسبت آپؐ کی

سب جہانوں ، سب زمانوں پر محیط
اور کیا ہے ؟ صرف رحمت آپؐ کی

آپؐ ہی پر تو نبوت ختم ہے
تا قیامت ہے نبوت آپؐ کی

کامیابی دُنیا و عقبیٰ کی کیا؟
کچھ نہیں ہے ، بس ہدایت آپؐ کی

آپؐ کے رستے پہ چلنا شرط ہے
مستند ہے گو شفاعت آپؐ کی

زَمِلُونی زَمِلُونی کی صدا
اے خدیجہؓ ! وُہ سعادت آپؓ کی

اے ابو بکرؓ و علیؓ و زیدؓ پاک
وُہ سعادت اور وُہ سبقت آپؓ کی

سب ہی سرشارِ نگاہِ خاص ہیں
کیسی بابرکت ہے صحبت آپؐ کی

وُہ حرا سے پھوٹنے والی کرن
روشنی جیسی شریعت آپؐ کی

نعت لکھنا، نعت پڑھنا کچھ نہیں
معتبر ہے بس، سماعت آپؐ کی

Memorization Without Comprehension: A Window onto the ‘Extremities’ of the Capability of Human Brain

Muslims across the world memorize the Quran in Arabic for verbatim recall. Memorizers can be native speakers of Arabic, non-native speakers of Arabic, or non-Arabic speakers. The purpose of this study is to investigate expert Quran memorizers on their memorization practices including what they brought to the act of memorization and what, according to them, underlay their success in memorization. Ten memorizers were interviewed about their reflections on their memorization practices. The analysis reveals that while some practices of the Quran memorizers are in line with findings from research literature on memory, there are others which are peculiar to them. The conclusion drawn is that Quran memorizers recite accurately because they do not learn the language. It is further concluded that Quran memorization is a special case, in which a range of extra linguistic factors such as identity, motivation and intention play an important role.

Synthesis and Characterization of Transparent Conducting Oxide Thin Films

To date state of art transparent conducting oxides (TCOs) material is tin doped indium oxide (ITO). It is due to its low electrical resistivity (⁓ 10-4 Ω-cm) and high optical transparency (more than 85 %) in the visible region. Though that material possesses superior optical and electrical properties but the production cost is very high due to limited resources of indium on earth. From application point of view, these films were prepared using very sophisticated techniques like sputtering and atomic layer deposition, which increases its cost. The inherent brittleness of ITO is big hindrance in its use on flexible substrates.To overcome these limitations, one has to explore an alternative material that is abundantly available and inexpensive too. Among various TCOs, zinc oxide (ZnO) is inexpensive, available in abundance, and it seems to be an alternative of ITO. Its optical properties are comparable to that of ITO but its electrical resistivity is rather on higher side. So the objective of thesis is to improve electrical and optical properties of ZnO thin films using inexpensive solution based method. The main objective of the thesis is to deposit ZnO thin film with pure c-texture because thin films with high c-texture possess better electrical and optical properties as compared to a texture and m-texture ZnO thin films. The texture of ZnO thin films can be easily controlled in magnetron sputtering and pulsed laser deposition technique but in solution based method it is very tricky. The effect of various dopants like Al, Cd, Ba, Li, and In, on the structural, optical, morphological, and electrical properties of the highly c-axis oriented ZnO thin films prepared using solution based method have been rarely reported. In most of the investigations, magnetron sputtering and pulsed laser deposition technique have been used.“Some other objectives include: (i) investigations of the effect of dopants mean-square amplitude of atomic vibrations < > or their Debye-Waller thermal parameter= 8 < > on the structural and optical properties of ZnO thin film, (ii) improvement in the electrical conductivity of un-doped and In-doped ZnO thin films using thermal treatment in N2 atmosphere, and (iii) to explore whether thin films prepared using solution based method possess any gas sensing ability or not? The thesis comprises of seven chapters: Chapter # 1 describes general, electrical, and optical properties of transparent conducting oxides. Chapter # 2 presents a discussion on ZnO thin films with c-, a-, and m-texture as well as a brief review about adjusting these textures by controlling the various deposition parameters in magnetron sputtering, pulsed laser deposition, chemical vapor deposition and solution based method. The “effect of various dopants on the c-texture of ZnO thin films” (mostly prepared by magnetron sputtering technique) have also been reviewed. Chapter # 3 reviews various deposition and characterization techniques for thin films. “Deposition techniques include sol-gel spin coating and spray pyrolysis. For characterization, x-ray diffraction (XRD), UV-Visible spectroscopy, Scanning electron microscopy (SEM), Fourier Transform Infrared Spectroscopy, Two Point and Four Point Probe technique, Hall effect, and Photoluminescence Spectroscopy have been used.” Chapter # 4 (original contribution) highlights the influence of Al, Ba, and Cd (concentration range 1%, 3%, and5%) on the optical, structural and electrical properties of highly c-axis oriented ZnO thin films. These thin films were prepared using sol-gel spin coating method.The effect of dopants mean-square amplitude of atomic vibrations < > or their Debye-Waller thermal parameter=8 < > on the properties” mentioned above have also been discussed. This aspect has been explored for the first time and never been reported before. Chapter # 5 (original contribution), deals with “the effect of Li dopant (concentration range 1%, 3%, and 5%) on the enhancement of the crystallite orientation along c-axis of ZnO thin film have been discussed. Its influence on the optical and electrical properties have also been studied. These films were also deposited using sol-gel spin coating method. Chapter # 6 (original contribution), presents the influence of a very wide range of In dopant concentration (0.2%, 0.4%, 0.6%, 0.8%, 1.0%, 1.25%, 1.5%, 2.0%, 2.5%, 5.0%, and 10%) on the optical, structural, and electrical properties of ZnO thin films using spray pyrolysis technique. Such a broad range of dopant concentration has never been explored and reported in the past. The effect of thermal treatment in N2 atmosphere on the physical properties of these thin films have also been investigated. Chapter # 7 (original contribution), highlights the gas sensing ability of In-doped ZnO thin films prepared using spray pyrolysis technique. These films show their potential ability to detect oxygen, and can be used as oxygen gas sensor. Chapter # 8 presents the conclusion from the original contribution Finally some suggestions have been given to extent this work in future. (A) Papers Published in Peer Reviewed International Journals from the Thesis 1. Dilawar Ali, M. Z. Butt, Conor Coughlan, David Caffrey, Igor V. Shvets, Karsten Fleischer: Nitrogen grain boundary passivation of In-doped ZnO transparent conducting oxide Physical Review Materials 2 (2018) 043402 2. Dilawar Ali, M.Z. Butt, Bilal Arif, Ahmed A. Al-Ghamdi, Fahrettin Yakuphanoglu: The role of Al, Ba, and Cd dopant elements in tailoring the properties of c-axis oriented ZnO thin films Physica B 506 (2017) 83–93 3. Dilawar Ali, M Z Butt, Bilal Arif, Abdullah G Al-Sehemi, Ahmed A Al-Ghamdi, Fahrettin Yakuphanoglu: Li induced enhancement in c-axis orientation and its effect on structural, optical, and electrical properties of ZnO thin films Mater. Res. Express 4 (2017) 026405 (B) Papers Published/Submitted in Peer Reviewed International Journals not included in the Thesis 1. Dilawar Ali, M. Z. Butt, Iqra Muneer, Farooq Bashir, Murtaza Saleem: Correlation between structural and optoelectronic properties of tin doped indium oxide thin films Optik 128 (2017) 235–246 2. Dilawar Ali, M. Z. Butt, I. Muneer, M. A. Farrukh, M. Aftab, M. Saleem, F. Bashir, A. U. Khan: Synthesis and characterization of sol-gel derived La and Sm doped ZnO thin films: A solar light photo catalyst for methylene blue Submitted for publication in Thin Solid Films (Submission date 16-07-2018)