Search or add a thesis

Advanced Search (Beta)
Home > Variational Models for Segmentation of Texture Images

Variational Models for Segmentation of Texture Images

Thesis Info

Access Option

External Link

Author

Shah, Hassan

Program

PhD

Institute

University of Engineering and Technology

City

Peshawar

Province

KPK

Country

Pakistan

Thesis Completing Year

2019

Thesis Completion Status

Completed

Subject

Mathemaics

Language

English

Link

http://prr.hec.gov.pk/jspui/bitstream/123456789/12309/1/Hassan%20Shah%20Maths%202019%20uet%20peshwr%20prr.pdf

Added

2021-02-17 19:49:13

Modified

2024-03-24 20:25:49

ARI ID

1676727658403

Asian Research Index Whatsapp Chanel
Asian Research Index Whatsapp Chanel

Join our Whatsapp Channel to get regular updates.

Similar


This dissertation is a contribution to computer vision and its analysis. The main work of this dissertation is to develop segmentation models for texture images. Texture segmentation aims at segmenting an image composed of textures, into distinct homogeneous regions with dissimilar texture features. For this purpose, some new variational texture image segmentation models are proposed. In these models, L0 norm smoothing and region based active contour approaches are utilized. Due to the smoothing and edge preserving properties of L0 gradient norm, the first proposed model utilizes L0 gradient norm for smoothing texture and minor details in the image and Mumford Shah data fidelity for segmentation. To get a texture free image, the model is minimized through alternating minimization algorithm and for segmentation, the model is minimized through Euler Lagrange’s equation. For efficient solution, the additive operator splitting method is applied to numerically solve the partial differential equations. As the L1 norm is more robust than L2 norm, therefore, in the next model, instead of the L2 norm, L1 norm is utilized in the data term and L0 gradient norm as a regularization for smoothing texture. For segmentation piecewise Mumford-Shah data term in level set formulation is used. Both the above models depend on the selection of initial contour and also producing staircasing problem. To resolve these issues, a convex variational model is proposed which is the unified form of L0 norm smoothing and convex minimization model. This model is independent of initial contour and overcome the problem of staircasing effect efficiently. Nevertheless, the model still producing problems when segmenting some hard textured images or when the image boundary is unclear and diffused. To overcome these problems, a joint smoothing and segmentation model by using piecewise smooth approximations is proposed. In this model, first, in the fidelity term instead of constant intensity means we approximated the image with piecewise smooth functions. Second, a signed pressure force function is utilized to stop the contours at minor or blurred boundaries and to speed up the process of contour movement. Third, L0 gradient norm is employed to smooth the textured image. In this dissertation, our second goal is to develop a texture image selective segmentation model. As in some cases it is very important to segment a region/part of interest from the whole image. Therefore to achieve this, some geometrical constraint are incorporated in the model. Furthermore, to fulfil our final goal, a multi-phase segmentation model via level set and L0 norm smoothing for texture images is proposed. This model may segment texture, noisy and inhomogeneous images more efficiently as compare to other state of the art models.
Loading...
Loading...

Similar Books

Loading...

Similar Chapters

Loading...

Similar News

Loading...

Similar Articles

Loading...

Similar Article Headings

Loading...

پروفیسر عبدالقوی دسنوی

پروفیسر عبدالقوی دسنوی مرحوم
افسوس، پروفیسر عبدالقوی دسنوی اس دنیا سے رخصت ہوئے، اِناﷲ وَاِنا اِلَیہ رَاجِعُون۔ ۷؍ جولائی کو وہ بھوپال کی خاک میں آسودہ خواب ہوئے تو اردو کی دنیا صرف ایک شریف، متین اور نشیط صاحب قلم سے ہی محروم نہیں ہوئی، ایسے مخلص، فعال بلک مجاہد انسان کو کھوبیٹھی جس کا تعلق اس جنس سے تھا جس کو اب نایاب ہی کہا جاسکتا ہے۔
دیسنہ ان کا وطن تھا، سادات کا یہ گاؤں بہار کیا پورے ہندوستان میں ممتاز اور منفرد تھا کہ اکثر باشندوں نے تعلیم قدیم و جدید دونوں کو یکساں اہمیت دی۔ کم ایسی بستیاں ہیں جن کی خاک سے مولانا سید سلیمان ندوی، سید ابوظفر ندوی، سید نجیب اشرف ندوی اور سید صباح الدین عبدالرحمن جیسی شخصیتیں اٹھیں اور علم و قلم کے بادل بن کر ملک کے مختلف خطوں کو سیراب کرگئیں۔
پروفیسر عبدالقوی بھی اسی سلسلہ ابروسحاب کا ایک حصہ تھے۔ بچپن، وطن میں ضرور گزرا جہاں مدرسۃ الاصلاح سے تعلیم کا آغاز ہوا، ۴۲ء میں وہ آرہ کے ہائی اسکول کی آٹھویں جماعت میں تھے لیکن پھر وہ بمبئی آگئے جہاں ان کے والد پروفیسر سید سعید رضا ندوی درس و تدریس کی ذمہ داریاں انجام دے رہے تھے، قوی صاحب نے بمبئی کے مشہور سینٹ زیویر اسکول میں اعلیٰ تعلیم حاصل کی، بمبئی گویا وطن ثانی تھا لیکن قدرت نے ان کے لیے بھوپال دارالاقبال کی سرزمین اس طرح مقدر کی کہ ۶۱ء میں سیفیہ کالج کے شعبہ اردو کی خالی جگہ کے لیے ایک درخواست اور اس کی قبولیت نے ان کو ’’بھوپال والے عبدالقوی دسنوی‘‘ بنادیا، بمبئی کے ہنگامہ خیز اور پرشور ماحول سے نکلے تو کوہساروں، بیابانوں کے نشیب و فراز اور ان کے دامن میں بکھرے زندگی کے تازہ و شاداب جلوؤں اور پرسکون ماحول کو پاکر محسوس کیا...

Kitabiyyah Mother and Ḥaḍanah of the Muslim Child: Religious and Legal Practices in Pakistan

The article attempts to analyze the religious and legal practices inside Pakistan regarding the issue of the kitabiyyah mother and ḥaḍanah of any Muslim child. The discussion primarily addresses the major issues emphasizing kitabiyyah mother and her relatives’ right to retain the custody of the Muslim child, and duration of ḥaḍanah under the supervision of kitabiyyah mother in shari‘ah and Pakistani Family Laws. Furthermore, it argues that kitabiyyah mother is permitted to raise the Muslim child according to her faith under both Islamic and Pakistani Family Laws. The article is delimited to the opinions of four Sunni schools of thoughts, Statute law, and Case laws. Nonetheless, in-depth comparative analysis has been carried out in most persuasive way to examine the rules related to kitabiyyah mother in custody of Muslim child after divorce under both Islamic Law, and Case Laws in Pakistan. Additionally, the existing similarities and differences consequent to religious differences have also been appropriately figured out to point out plausible way forward to address prevailing schism. Contradictions between the legal practices and Islamic law need keen attention Islamic and legal scholars to carefully craft to harmonize both in the best interest of child.

Fabrication and Investigation of Organic and Nano Materials Based Sensors

This work presents the fabrication and investigation of organic and nano materials based sensors for humidity, temperature and electromechanical applications. Polyaniline (PANI), orange dye (OD)-PANI composite and of cellulose- poly-N-epoxypropylcarbazole (PEPC) have been used for the fabrication of surface type humidity sensors. The sensors are fabricated by depositing films of various thicknesses on glass substrates between pre-deposited metallic electrodes. The sensing mechanism is based on the impedance and capacitance variations due to the absorption or desorption of water vapors. The consequences of annealing, measuring frequency and absorption-desorption behavior of the sensor have been discussed in detail. For all sensors impedance-humidity relationship shows more uniform change as compared to capacitance- humidity relationship in the given range humidity. The temperature sensors have been fabricated by using multiwalled carbon nanotubes (MWCNTs), V2O4-PEPC composite and CuPc on n-GaAs. The CNTs based sensors are fabricated by the deposition CNT nanopowder on a paper substrate and on adhesive elastic polymer tape. The nominal thickness of the CNT films on paper substrates is 30–40 μm while that of elastic substrate is ~ 300-430 μm. The DC resistance of the sensors decreases with increase in temperature. For both types‘ sensors, the resistance-temperature relationship shows wide range sensitivity. The V2O4-PEPC composite based temperature sensors are fabricated by drop-casting the blend of composite into the gap between preliminary deposited silver electrodes on glass substrates. The thickness of the V2O4-PEPC films is in the range of 20-40 μm. It is found that with increase in temperature the AC resistance of the samples decreases by 10-12 times. The response recovery time is also measure. The Ag/p-CuPc/n-GaAs/Ag cells are fabricated by the deposition of p-type copper phthalocyanine on n-type GaAs single-crystal semiconductor substrate. The temperature sensing and photoconductive behavior of the cells are investigated. The results reveal that with increase in temperature from 33-75 °C the resistance temperature coefficients (RTC) for the reverse and forward bias resistances are equal to -2.0 %/°C and -1.5 %/°C, respectively. Electromechanical sensors based on PANI, CNTs and CNTs-Cu2O composites have been fabricated and investigated. The 20-80 μm thick PANI films are deposited by drop-casting on Ag electrodes, which are preliminary deposited on glass substrates. The effect of displacement on the resistance and capacitance of film is investigated. It is observed that with increases in displacement the resistance decreases and the capacitance increases. For the fabrication of CNT–Cu2O composite based pressure sensors tablets of composite are made at a pressure of 353 MPa. The average diameter and the average thickness of the tablets are 10 mm and 4 mm, respectively, and both sides of the tablet are covered by silver paste. By varying pressure from 0-37 kN/m2, the change in DC resistance of the sensor is measured. The CNTs and CNTs–Cu2O composite based strain sensors have been fabricated by pressed tablets and elastic polymer beam. The 1 mm thick tablets of CNTs and CNTs–Cu2O composite are fabricated at a pressure of 200-300 MPa and 353MPa, respectively. The samples are installed on the polymer elastic beam by glue. The electric contacts to the samples are made by silver paste. The inter-electrodes distance (length) and diameter of the surface-type samples are in the range of 6–8 mm and 10 mm, respectively. It is found that DC resistance of the strain sensors increases under tension and decreases under compression, while the average strain sensitivities are in the range of 50-80 and 44–46 for CNTs and CNTs–Cu2O composite based sensors, respectively.