Development of Improved Saliency Detection Techniques / (Record no. 615919)
[ view plain ]
| 000 -LEADER | |
|---|---|
| fixed length control field | 04683nam a22001697a 4500 |
| 003 - CONTROL NUMBER IDENTIFIER | |
| control field | NUST |
| 082 ## - DEWEY DECIMAL CLASSIFICATION NUMBER | |
| Classification number | 005.1,KAN |
| 100 ## - MAIN ENTRY--PERSONAL NAME | |
| Personal name | Kanwal, Maria |
| 9 (RLIN) | 35176 |
| 245 ## - TITLE STATEMENT | |
| Title | Development of Improved Saliency Detection Techniques / |
| Statement of responsibility, etc. | Maria Kanwal |
| 260 ## - PUBLICATION, DISTRIBUTION, ETC. | |
| Place of publication, distribution, etc. | Rawalpindi, |
| Name of publisher, distributor, etc. | MCS (NUST), |
| Date of publication, distribution, etc. | 2022 |
| 300 ## - PHYSICAL DESCRIPTION | |
| Extent | xviii, 134 p |
| 505 ## - FORMATTED CONTENTS NOTE | |
| Formatted contents note | Saliency is the perceptual quality by which an observable thing or object stands out relative<br/>to its environment. It is that property by which some object stands out. Accurate detection<br/>of salient object is a challenging task. In this thesis, novel and robust saliency detection<br/>techniques and their different applications are proposed to detect salient objects from images.<br/>Different features of images are utilized to extract accurate saliency maps.<br/>The first proposed technique formalizes the saliency map using color and depth along<br/>with input’s histogram. The color saliency map assumes that the salient objects in an image<br/>are usually more colorful than objects that are not salient. Likewise, the salient objects are<br/>usually found closer to the camera during acquisition; therefore, the transmission map is also<br/>utilized for saliency detection. The third map is estimated from the histogram. These three<br/>maps are then fused and filtered in order to yield a smooth saliency map.<br/>The second proposed technique is based on texture contrast and convex hull center prior<br/>maps. Input image is first segmented into super-pixels. Primary saliency map is constructed<br/>using texture features. Convex-hull-based center prior map is extracted and refined with<br/>graph regularization to obtain secondary map. Primary and secondary maps are fused based<br/>on weight matrix. Thresholding and filtering are applied to obtain final map.<br/>The third proposed technique is frequency and gradient domain saliency detection using<br/>pyramid approach. The edges of the input image are sharpened first. Pyramid decomposition<br/>at different scales is applied. At each scale, the color space of the RGB image is converted<br/>into YIQ to extract the Q channel. In the frequency domain, Butterworth high-pass filtering<br/>is applied. Gradient and DoG filters are applied. Each channel’s saliency map is created via<br/>region filling. The saliency maps of pyramids at different scales are integrated and filled.<br/>The fourth proposed saliency detection technique is for underwater images. The input<br/>image is enhanced and gradient domain filtering is applied. The filtered image undergoes<br/>a pyramid decomposition. Saliency is computed on three different scales on two parallel<br/>steps. In first step, saliency is computed using cellular automata at each scale. The map is<br/>further optimized and filtered to obtain saliency at a given scale. A primary saliency map is<br/>computed by scale integration. In second step, saliency is computed using a homomorphic<br/>filter on each scale. Guided filter is applied to obtain saliency at a given scale. Secondary<br/>saliency map is computed by scale integration. Multiplicative fusion is applied on primary<br/>and secondary saliency maps to obtain final output.<br/>In the fifth proposed technique, saliency based fabric defect detection via bag-of-words<br/>iv<br/>model is proposed. The proposed methodology feeds the fabric images into the framework.<br/>The proposed saliency technique is used to create saliency maps of fabric images. The kmean<br/>clustering algorithm is used to extract local features. A bag of features is created<br/>using cluster centers. To detect defected fabric, feature vectors are used to train a K-Nearest<br/>Neighbor (K-NN) classifier.<br/>In the sixth proposed technique, it is proposed to direct the user’s attention to a specific<br/>region of interest (ROI). To begin with, a bilateral filter is used to smooth ROI by removing<br/>unwanted details from the defocus map. After that, the hue component of the ROI is adjusted,<br/>and the outline is extracted using neighboring data. Lastly, the hue component is used to<br/>direct the viewer’s attention to a specific region in the resultant image’s outline.<br/>Cutting-edge existing techniques are used to compare the proposed techniques. Experiments<br/>demonstrate the significance of proposed techniques on various datasets. The simulation<br/>results show that the proposed techniques produce better results that are noise-free<br/>and very close to the ground truth. These salient detection techniques can be used in various<br/>applications like image and video compression, object tracking, image segmentation, etc. |
| 650 ## - SUBJECT ADDED ENTRY--TOPICAL TERM | |
| Topical term or geographic name entry element | PhD Computer Software Engineering Thesis |
| 9 (RLIN) | 132801 |
| 651 ## - SUBJECT ADDED ENTRY--GEOGRAPHIC NAME | |
| Geographic name | PhD CSE Thesis |
| 9 (RLIN) | 132802 |
| 700 ## - ADDED ENTRY--PERSONAL NAME | |
| Personal name | Supervised by Dr. Abdul Ghafoor |
| 9 (RLIN) | 132894 |
| 942 ## - ADDED ENTRY ELEMENTS (KOHA) | |
| Source of classification or shelving scheme | |
| Koha item type | Thesis |
| Withdrawn status | Lost status | Source of classification or shelving scheme | Damaged status | Not for loan | Permanent Location | Current Location | Shelving location | Date acquired | Total Checkouts | Full call number | Barcode | Date last seen | Price effective from | Koha item type | Public note |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Military College of Signals (MCS) | Military College of Signals (MCS) | Thesis | 01/26/2026 | 005.1,KAN | MCSPhD CSE-15 | 01/26/2026 | 01/26/2026 | Thesis | Almirah No.68, Shelf No.5 |