Aim at the moving objects detection, after studying several categories of background modeling methods, we design an improved Vibe algorithm based on image segmentation algorithm. Vibe algorithm builds background model via storing a sample set for each pixel. In order to detect moving objects, it uses several techniques such as fast initialization, random update and classification based on distance between pixel value and its sample set. In our improved algorithm, firstly we use histograms of multiple layers to extract moving objects in block-level in pre-process stage. Secondly we segment the blocks of moving objects via image segmentation algorithm. Then the algorithm constructs region-level information for the moving objects, designs the classification principles for regions and the modification mechanism among neighboring regions. In addition, to solve the problem that the original Vibe algorithm can easily introduce the ghost region into the background model, the improved algorithm designs and implements the fast ghost elimination algorithm. Compared with the tradition pixel-level background modeling methods, the improved method has better  robustness and reliability against the factors like background disturbance, noise and existence of moving objects in the initial stage. Specifically, our algorithm improves the precision rate from 83.17% in the original Vibe algorithm to 95.35%, and recall rate from 81.48% to 90.25%. Considering the affection of shadow to moving objects detection, this paper designs a shadow elimination algorithm based on Red Green and Illumination (RGI) color feature, which can be converted from RGB color space, and dynamic match threshold. The results of experiments demonstrate  that the algorithm can effectively reduce the influence of shadow on the moving objects detection. At last this paper makes a conclusion for the work of this thesis and discusses the future work.

The objective of this study is to apply digital image processing (DIP) techniques to optical coherence tomography (OCT) images and develop computer-based non-subjective quantitative analysis, which can be used as diagnostic aids in early detection of dental caries. This study first compares speckle reduction effects on raw OCT image data by implementing spatial-domain and transform-domain speckle filtering. Then region-based contour search and global thresholding techniques examine digital OCT images with possible lesions to identify and highlight the presence of features indicating early stage dental caries. The outputs of these processes, which explore the combination of image restoration and segmentation, can be used to distinguish lesion from normal tissue and determine the characteristics prior to, during, and following treatments. The combination of image processing and analysis techniques in this thesis shows potential of detecting early stage caries lesion successfully.

Spaceborne Synthetic Aperture Radar (SAR) is commonly considered a powerful sensor to detect sea ice. Unfortunately, the sea-ice types in SAR images are difficult to be interpreted due to speckle noise. SAR image denoising therefore becomes a critical step of SAR sea-ice image processing and analysis. In this study, a two-phase approach is designed and implemented for SAR sea-ice image segmentation. In the first phase, a Gamma-based bilateral filter is introduced and applied for SAR image denoising in the local domain. It not only perfectly inherits the conventional bilateral filter with the capacity of smoothing SAR sea-ice imagery while preserving edges, but also enhances it based on the homogeneity in local areas and Gamma distribution of speckle noise. The Gamma-based bilateral filter outperforms other widely used filters, such as Frost filter and the conventional bilateral filter. In the second phase, the K-means clustering algorithm, whose initial centroids are optimized, is adopted in order to obtain better segmentation results. The proposed approach is tested using both simulated and real SAR images, compared with several existing algorithms including K-means, K-means based on the Frost filtered images, and K-means based on the conventional bilateral filtered images. The F1 scores of the simulated results demonstrate the effectiveness and robustness of the proposed approach whose overall accuracies maintain higher than 90% as variances of noise range from 0.1 to 0.5. For the real SAR images, the proposed approach outperforms others with average overall accuracy of 95%.

This memo describes the initial results of a project to create aself-supervised algorithm for learning object segmentation from videodata. Developmental psychology and computational experience havedemonstrated that the motion segmentation of objects is a simpler,more primitive process than the detection of object boundaries bystatic image cues. Therefore, motion information provides a plausiblesupervision signal for learning the static boundary detection task andfor evaluating performance on a test set. A video camera andpreviously developed background subtraction algorithms canautomatically produce a large database of motion-segmented images forminimal cost. The purpose of this work is to use the information insuch a database to learn how to detect the object boundaries in novelimages using static information, such as color, texture, and shape.This work was funded in part by the Office of Naval Research contract#N00014-00-1-0298, in part by the Singapore-MIT Alliance agreement of11/6/98, and in part by a National Science Foundation Graduate StudentFellowship.

The success of tourism, at a destination, is often accredited to the strength of its marketing; yet, the marketing environment is changing at a fast pace where developments in digital technology have had a profound effect on marketing strategies. Furthermore, the increased accessibility of long and short haul travel has resulted in greater competition for tourist visits among destinations. Such changes present a challenge for cold water island destinations with a seasonal tourism product and limited resources for destination marketing. The ability of such destinations to adopt target marketing strategies, using meaningful segmentation criterion, is of great importance for their future success. For cold water islands, it is vital that the promotional message resonates with the target audience, as such, an image segmentation is proposed. Although tourist segmentation is well practiced in tourism research, existing studies focus on socio-demographic or behavioural segmentation. Few studies have conducted image based segmentation, thus, this thesis explores the feasibility of image segmentation in cold water island destinations; using the Isles of Scilly as a case study. In this thesis image segmentation is used to develop a typology of visitors to the Isles of Scilly, and the intrinsic relationships between destination image, motivation, behaviour, evaluation and place attachment are also explored. Due to the difficulties in measuring image, a mixed method approach was adopted and a concurrent triangulation design employed. Quantitative data were collected from 500 ii respondents visiting the Isles of Scilly, by means of a face-to-face questionnaire, and a further 15 in-depth interviews formed the qualitative sample. Quantitative data were analysed using Exploratory Factor Analysis and K-means Cluster Analysis, while qualitative data were analysed using Thematic Content Analysis. The findings of this thesis revealed the feasibility of image segmentation, through the creation of a six-fold typology of visitors to the Isles of Scilly. Both theoretical and practical implications were derived from this study. The most significant theoretical contribution of this research is that offered to the understanding of image segmentation, as this is the first study conducted in the context of cold water islands. Theoretical contributions were also made with regard to the intrinsic relationships between destination image and motivation, behaviour, evaluation and place attachment. While findings of this study agreed with those of past research, valuable contributions are also offered. Notably, this study adds to a body of work relating to the relationships between complex image and motivation, on-site behaviour, evaluation and place attachment. Additionally, this study adds to tourism knowledge, where the role of on-site behaviour in the formation of positive image, and the influence of participation in special interest tourism, on the formation of destination image are identified. Furthermore, practical recommendations are provided in relation to marketing of the Isles of Scilly where lucrative image segments are identified. Finally, through the understanding of destination image, this thesis proposes seasonal marketing campaigns and the development of special interest tourism, with a focus on wildlife, in order to successfully promote and develop tourism in the Isles of Scilly.

Banana has become the most commonly consumed fresh fruit among US population. It is a challenge to use computer vision to divide touching bananas, for this purpose a novel image segmentation algorithm is proposed, combining k-means and the watershed transformation. The first part is to extract the background, achieved using a K-means based in the HS space, the second part is individual banana segmentation where a smarter selection of the initial markers from where the watershed transformation grows is attained fusing two morphological filters with different structural elements. The validation of the proposed algorithm has been conducted using 124 experimentally capture banana pictures manually segmented. For background extraction K-means in HS space produced the best performance over the other two tested (Otsu, K-means(L*a*b*), getting average a F1 Score average of 96.99%, Otsu and K-means(L*a*b*) scored 82.58% and 88.06% respectively. The result of the watershed segmentation was also compared with the manual segmentation; The overall performance using the F1 Score in average is 92.28%. The performance would improve with modifications to the system, including a more homogenous illumination, only allowing certain positions to be possible for the bananas cluster, and a more adequate background selection.

abstract: Two critical limitations for hyperspatial imagery are higher imagery variances and large data sizes. Although object-based analyses with a multi-scale framework for diverse object sizes are the solution, more data sources and large amounts of testing at high costs are required. In this study, I used tree density segmentation as the key element of a three-level hierarchical vegetation framework for reducing those costs, and a three-step procedure was used to evaluate its effects. A two-step procedure, which involved environmental stratifications and the random walker algorithm, was used for tree density segmentation. I determined whether variation in tone and texture could be reduced within environmental strata, and whether tree density segmentations could be labeled by species associations. At the final level, two tree density segmentations were partitioned into smaller subsets using eCognition in order to label individual species or tree stands in two test areas of two tree densities, and the Z values of Moran's I were used to evaluate whether imagery objects have different mean values from near segmentations as a measure of segmentation accuracy. The two-step procedure was able to delineating tree density segments and label species types robustly, compared to previous hierarchical frameworks. However, eCognition was not able to produce detailed, reasonable image objects with optimal scale parameters for species labeling. This hierarchical vegetation framework is applicable for fine-scale, time-series vegetation mapping to develop baseline data for evaluating climate change impacts on vegetation at low cost using widely available data and a personal laptop. / Dissertation/Thesis / M.A. Geography 2013

Image compression based on Region of Interest (ROI) has been one of the hot topics of interest in image processing. There is not a single widely accepted method for detecting the ROI automatically form an image. To reduce the transmission bandwidth and storage space requirements of gray scale images, an algorithm is suggested for detecting the ROI automatically based on Tsallis entropy method. Tsallis entropy method is used to segment the image into two segments, the ROI and the background. These two segments can then be compressed at different rates, to avoid losing information in the ROI while achieving a good compression. Different approaches of compression based on wavelets and use of various compression methods are also discussed.

The thesis focuses on segmentation of images with leaves of woody species. The aim was to investigate existing image segmentation methods, choose suitable method for given data and implement it. The chosen method should segment existing datasets, photographs from cameras as well as photographs from lower-quality mobile phones. Inputs are scanned leaves and photographs of various quality. The thesis summarizes the general methods of image segmentation and describes own algorithm that gives us the best results. Based on the histogram, the algorithm decides whether the input is of sufficient quality and can be segmented by Otsu algorithm or is not and should be segmented using GrowCut algorithm. Next, the image is improved by morphological closing and holes filling. Finally, only the largest object is left. Results are illustrated using generated output images. Powered by TCPDF (www.tcpdf.org)

Body image is undoubtedly important in everyone's life. The main objective of this thesis is to find its importance for marketing. To achieve this goal, it was necessary to find out the society's opinions on the issue of beauty and body image, how do media picture human body and if there exists a difference between these two things. The first part of this theses consists of the historical development of the beauty ideal. It is followed by segmentation of Czech population, based on the data from the project MML-TGI, survey focused on beauty preferences and content analysis of lifestyle magazines. The findings support among other things the importance of beauty to most people, media's focus on extreme thinness for females and disparity between the presented ideal and people's preferences. The results lead to one conclusion: the importance of body image for marketing exists and is significant.