Search or add a thesis

Advanced Search (Beta)
Home > Facial Expression Recognition in Unconstrained Environment

Facial Expression Recognition in Unconstrained Environment

Thesis Info

Access Option

External Link

Author

Khan, Sajid Ali

Program

PhD

Institute

Shaheed Zulfikar Ali Bhutto Institute of Science and Technology

City

Karachi

Province

Sindh

Country

Pakistan

Thesis Completing Year

2019

Thesis Completion Status

Completed

Subject

Computer Science

Language

English

Link

http://prr.hec.gov.pk/jspui/bitstream/123456789/12765/1/Sajid%20Ali%20Khan_CS_2019_SZABIST_PRR.pdf

Added

2021-02-17 19:49:13

Modified

2024-03-24 20:25:49

ARI ID

1676727757407

Asian Research Index Whatsapp Chanel
Asian Research Index Whatsapp Chanel

Join our Whatsapp Channel to get regular updates.

Similar


Facial expressions are the most effective form of non-verbal communication which is used to express one’s emotions. It not only expresses our expressions, but also communicates a wealth of information during social interaction. Facial expressions play an important and effective role in Human-Computer Interaction. Unlike humans, facial expression recognition is a challenging task for computers and research work in this domain can still be considered in seminal form. The prevalent facial expression techniques tend to provide accurate and impressive results for the images captured under controlled environment with a cooperative subject. However, majority of these techniques fail to provide adequate results for the images captured in uncontrolled environment. Achieving a higher classification accuracy rate for the images captured in uncontrolled environments is a major challenge being faced by researchers in this domain. There are many factors such as illumination, image orientations, noise and low-resolution, which hinder the development of facial expression recognition system in uncontrolled environment. Even the datasets prepared under the constrained environments sometimes need preprocessing before the classification stage. The core objective of this dissertation is to analyze existing techniques and develop an effective framework that is capable of classification of human facial expressions both under constrained and unconstrained environments. In this dissertation, we have explored, investigated and proposed frameworks to deal with two of the most common, influential and challenging issues that affect the accuracy of a facial expression recognition for images captured in an uncontrolled environment, namely illumination and low-resolution. First, a novel framework for feature extraction named Weber Local Binary Image Cosine Transform has been developed which not only extracts significant features by integrating features extracted using local binary pattern and weber local descriptor but also utilizes most discriminant features by applying the frequencybased components. Low-resolution and multi-orientation facial images have been used for the classification and a significant improvement in the classification accuracy rate has been achieved with the proposed framework. The developed framework has proved to be not only reliable but also computationally efficient across multiple datasets in the presence of noise and orientations. The Proposed framework has been tested on four datasets including JAFEE, MMI, CK+ and SFEW datasets. The second major contribution is the development of an illumination invariant technique. The proposed framework has been named Weber Local Binary Image Cosine Transform (WLBI-CT) and it advocates for the need of simultaneous contrast enhancement and brightness preservation for datasets containing real world images in unconstrained environment. The empirical results for the SFEW dataset are promising. In order to evaluate the performance of the proposed framework, rigorous set of experiments are presented in this thesis. The empirical results meet the standard quantitative measure criteria. The comparison of our work with various other stateof-the-art techniques is also presented using various benchmarks for these factors. The results are impressive even in the case of inclusion of noise and occlusion effects.
Loading...
Loading...

Similar Books

Loading...

Similar Chapters

Loading...

Similar News

Loading...

Similar Articles

Loading...

Similar Article Headings

Loading...

شفیق آصف

آؤ خود کو ڈھونڈتے ہیں،،

جانے کب سے کھو چکا ہوں شہر میں

جانے کب سے اپنا چہرہ ڈھونڈتا پھرتا ہوں میں

شہر کے ان راستوں میں

کس قدر تنہائی ہے

ہر کوئی تنہائیوں کی

بھیڑ میں کھویا ہوا ہے

یوں تو سورج کا اجالا ضوفشاں ہے

پھر بھی گلیوں میں ابھی تک

تیرگی سی ہے رواں

ایسے عالم میں بھلا ہم

کیسے ڈھونڈیں خود کو اپنے شہر میں

شہر اپنا ہےمگر ہم

ڈھونڈتے پھرتے ہیں خود کو

جانے کب دیکھیں گے ہم اک آشنا چہرہ کوئی

گر یہاں کوئی ہمارا آشنا چہرہ نہیں تو

آؤ خود کو ڈھونڈ لیں

آؤ خود کو دیکھ لیں

شہر کی اس بھیڑ میں

اسلامی تعلیمات جنگ و امن میں انسانی اقدار کا لحاظ و تحفظ: ایک تحقیقی مطالعہ

Islam is a globally divine religion and a complete code of life that directs its believers in every sphere of life. Islam always strives for the development of peace and harmony, condemns war and allow it only for the sake of self-defence and protection but as war is a peculiar human activity especially in this global era, thus, Islam has determined appropriate principles for both War and Peace. Muslim attitudes to war and peace are based on the teachings of the Qur'an and the Holy Prophet (Peace be upon him). One of the salient feature of these teachings is giving considerable importance and protection to human values. The article in hands presents a research analysis of Islamic human-friendly Principles and Ethics of War and Peace.

Assessment and Geo-Statistical Modeling of Fluoride Pollution Around Brick Kilns in Rawalpindi / Islamabad, Pakistan.

Geographical Information System (GIS) is an emerging field of Environmental Science. Today with the rapid population growth and demand for more developments, the environmental issues are growing and resulting in more diversifying environmental problems especially pollution. This research reveals the importance of the spatial module of information which is a measure of the pollution data. In the present study, data of three years were managed, processed, evaluated and visualized by GIS and raster calculations. The results revealed the possible spatial relationship within environmental parameters and pollution. This thesis describes the broad range of geo-spatial modeling as well as some defies related to it. The objectives of the present study were to identify the spatial gradient pattern and distribution trend of fluoride pollution and its effect on the crops (wheat and maize) in vicinity of brick kilns (source of fluoride pollution) using geo-spatial and geo-statistical techniques. Besides statistical techniques were also employed to observe the distributional pattern using centrographic technique, identified the hotspots, the risk of pollution for nearby areas based on weighting distance interpolation technique and Kriging approach for more accurate estimation. Total 93 kilns were identified in Islamabad and three Tehsils of Rawalpindi, where wheat and maize crops were cultivated in the fields around the kilns. The sample number of plants and soil was 251 and 144 for summer and winter season respectively. More significant leaf injury to maize crop was observed in the summer compared to the wheat crop in winter. This observation was supported by Vegetation Index (VI), calculated by raster calculator. The results of chemical analysis indicated that fluoride concentrations (6.8 ppm, 14.3 ppm, 13.6 ppm, 13.9 ppm) were observed in the wheat plant samples of Jhangi syedan, Chakri, GT road, Mohra and maximum fluoride concentration (29.6 ppm, 29.45 ppm, 29.71 ppm, 29.41 ppm) was observed during the summer in maize plant samples of Bhatta road, Gurha, Dhok Niazu and Dhok Gujran in the year 2017. However, fluoride concentration in samples varied according to the spatial location with climatic condition. A dataset of Islamabad, Tehsil Rawalpindi, and Tehsil Gujarkhan showed significant positive spatial autocorrelation and clustering pattern, while no significant spatial correlation was found in the data set of Kallar syedan, but still significant hotspots were identified. A majority of hotspot for fluoride pollution was identified in the maize fields of Rawalpindi and Gujarkhan, in all study years. Furthermore, semivariogram based Kriging model indicated Islamabad, Northwest Rawalpindi, East Gujarkhan more at risk of fluoride pollution. Inverse distance weighting and Kriging Model also exhibited that effect on plants and soil gets reduced with increasing distance from the kiln. But the extent of the effect was only shown by the Ordinary Kriging Model. Climatic data marked temporal effect of fluoride variation in study areas during the study period. It was observed that high precipitation resulted into negligible fluoride effect and concentration, whereas less and no precipitation resulted into more fluoride effect and concentration. Similarly, positive correlation was found between temperature and fluoride pollution and effect. The effect of pollution was greater along distance at high temperature and effectively reduced by the distance in lesser temperature. It was necessary to screen out the current status of existing kilns and to evaluate the effect on nearby environmental parameters. Accordingly, this research highlighted the effect of fluoride pollution release from the kilns to soil and crops and revealed the spatial distribution pattern and extent of pollution using modeling technique.