Feature extraction of segmented skin lesions is a pivotal step for implementing accurate decision support systems. Existing feature sets combine many ad-hoc calculations and are unable to easily provide intuitive diagnostic reasoning. This thesis presents the design and evaluation of a set of features for objectively detecting melanoma in an intuitive and accurate manner. We call these "high-level intuitive features" (HLIFs). The current clinical standard for detecting melanoma, the deadliest form of skin cancer, is visual inspection of the skin's surface. A widely adopted rule for detecting melanoma is the "ABCD" rule, whereby the doctor identifies the presence of Asymmetry, Border irregularity, Colour patterns, and Diameter. The adoption of specialized medical devices for this cause is extremely slow due to the added temporal and financial burden. Therefore, recent research efforts have focused on detection support systems that analyse images acquired with standard consumer-grade camera images of skin lesions. The central benefit of these systems is the provision of technology with low barriers to adoption. Recently proposed skin lesion feature sets have been large sets of low-level features attempting to model the widely adopted ABCD criteria of melanoma. These result in high-dimensional feature spaces, which are computationally expensive and sparse due to the lack of available clinical data. It is difficult to convey diagnostic rationale using these feature sets due to their inherent ad-hoc mathematical nature. This thesis presents and applies a generic framework for designing HLIFs for decision support systems relying on intuitive observations. By definition, a HLIF is designed explicitly to model a human-observable characteristic such that the feature score can be intuited by the user. Thus, along with the classification label, visual rationale can be provided to further support the prediction. This thesis applies the HLIF framework to design 10 HLIFs for skin cancer detection, following the ABCD rule. That is, HLIFs modeling asymmetry, border irregularity, and colour patterns are presented. This thesis evaluates the effectiveness of HLIFs in a standard classification setting. Using publicly-available images obtained in unconstrained environments, the set of HLIFs is compared with and against a recently published low-level feature set. Since the focus is on evaluating the features, illumination correction and manually-defined segmentations are used, along with a linear classification scheme. The promising results indicate that HLIFs capture more relevant information than low-level features, and that concatenating the HLIFs to the low-level feature set results in improved accuracy metrics. Visual intuitive information is provided to indicate the ability of providing intuitive diagnostic reasoning to the user.

No description available.

Computer assisted surgery uses a collection of different techniques including but not limited to: CT-guided, fluoroscopy-guided, and ultrasound-guided imaging which allows medical staff to view bony anatomy of a patient in relation to surgical tools on a computer screen. By providing this visual data to surgeons less invasive surgeries can be performed on a patient's fractured scaphoid. The data required for a surgeon to perform a minimally invasive surgery while looking only at a computer screen, and not directly at a patient's anatomy, will be provided by CT and ultrasound data. We will discuss how ultrasound and CT data can be used together to allow a minimally invasive surgery of the scaphoid to be performed. In this thesis we will explore two techniques of registering segmented ultrasound images to CT data; an Iterative Closest Point (ICP) approach, and an Unscented Kalman Filter-based Registration (UKF). We use two different ultrasound segmentation methods; a semi-automatic segmentation, and a Bayesian segmentation technique. The segmented ultrasound data is then registered to a CT volume. The success or failure of the registrations is measured by the error calculated in mapping the corresponding land- marks to one another and calculating the target registration error. The results show that the Unscented Kalman Filter-based registration using the Bayesian segmentation of ultrasound images has the least registration error, and has the most robustness to error in initial alignment of the two data sets. / Thesis (Master, Computing) -- Queen's University, 2010-05-28 11:17:31.934

An area scan colour camera was used to acquire images of single kernels of Canada Western Red Spring (CWRS) wheat from different growing locations (nine locations in the year 2007, eight locations in the years 2008 and 2009) in Western Canada. Two sample presentation methods were used. In the first method, fifteen kernels from a single location were imaged in a single image and in the second method one kernel from each location were imaged in the same image. Images of individual kernels of barley and rye were also acquired for a classification study. Bulk images of heaped and flat CWRS samples, heaped and flat barley samples, and images of CWRS wheat mixed with different proportion of foreign materials (0%, 2%, 5%, 10%, 20% barley) were acquired. Morphological, colour, and textural features from single kernel images and colour and textural features from bulk grain images were extracted by a program developed by researchers at the Canadian Wheat Board Centre for Grain Storage Research. The top 30 features from the single kernel images of CWRS wheat samples from different growing locations and also different crop years were compared by Scheffe's test. Image features from two types of presentation methods were also compared. Representative of a composite sample which was generated by randomly selecting kernels from each location was compared with individual locations. Three-way classification of CWRS wheat, barley, and rye was done using the top 30 features. For bulk grain image analysis, features from flat bulk grain samples and heaped bulk grain samples were extracted and compared. Image features of CWRS wheat mixed with different percentages of barley were examined, and a cross-validation discriminant classifier was developed to classify CWRS wheat mixed with different percentages of barley. Classifications were also conducted using flat grain as training, flat and heaped grain in testing. Results from this study indicated that most image features from different growing locations and also different crop year samples had significant differences. However, these differences did not influence three-way classification of CWRS wheat, barley, and rye. Features from the composite sample were compared with those from each location. Composite sample features were different from each location. Hence composite samples may not be representative for all locations. However three-way classification using composite sample features gave similar results as in the case of using each location samples. Canada Western Red Spring wheat and barley samples were used in comparing the image features of flat grain and heaped grain. Results indicated that image features from flat grain were different from heaped grain samples. However a two-way classification applied to heaped and flat CWRS wheat, and also heaped and flat barley, gave perfect classification accuracies. Classification models trained using flat grain also gave perfect classification accuracies when tested using flat and heaped grain. A comparison of the top 30 features extracted from images of CWRS wheat mixed with different proportion of barley revealed that grain image features changed after mixing barley. In classification of CWRS wheat mixed with 0, 2, 5, 10, and 20% barley, classification accuracies of 100, 99, 96, 95, and 98% were obtained, respectively.

Feature-based attention refers to the phenomenon that attending to a feature value (e.g., a specific shade of red) enhances the detection of similar feature values (e.g., the same shade of red or other shades of red similar to the attended shade) relative to different feature values (e.g., green) that belong to a different object, and that this facilitation effect can be found across the visual field. In previous studies, the participants’ task was primarily the detection or discrimination of simple features such as orientation, colour or motion. The experiments reported in this thesis investigated whether feature-based attention could also influence the speed and/or accuracy of discriminating alphanumeric stimuli such as letters and numbers. In three experiments, participants saw displays that consisted of a series of stimulus patterns at a central location followed by the appearance of an alphanumeric stimulus at one of two peripheral locations. Experiment 1 tested whether paying attention to a specific orientation in a central stimulus would affect the speed and/or accuracy of identifying a peripheral letter whose principal axis was either the same as or different from the attended orientation of the central stimulus. Experiment 2 changed the peripheral stimulus from a letter to a number. In Experiment 3, a peripheral stimulus occurred randomly on 50% of the trials instead of on 100% of the trials. The results showed that attending to a specific orientation of a central stimulus could affect the processing efficiency of both letters and numbers at a peripheral location when the alphanumeric stimulus occurred on every trial (Experiments 1 and 2), but not when it appeared on 50% of the trials. These results suggest that feature-based attention could influence the identification of alphanumeric stimuli. However, the effect may be quite short-lived.

This research focuses on the development of a persistent navigation algorithm for a hovering vehicle with a single, downward-facing visible spectrum camera. A successful persistent navigation algorithm allows a vehicle to: * Continuously estimate its location and pose within a local, if not global, coordinate frame. * Continuously align incoming data to both temporally proximal and temporally distant data. For aerial images, this alignment is equivalent to image mosaicking, as is commonly used in aerial photogrammetry to produce broad-scale photomaps from a sequence of discrete images. * Operate relative to, and be commanded relative to the sensor data, rather than relative to an abstract coordinate system. The core application space considered here is moderate-to-high altitude aerial mapping, and a number of sets of high-resolution, high-overlap aerial photographs are used as the core test data set. These images are captured from a sufficient altitude that the apparent perspective shift of objects on the ground is minimized -- the scene is effectively planar. As such, this research focuses heavily on the properties and advantages available when processing such planar images. This research is split into two threads which track the two main challenges in visual persistent navigation: the association and alignment of visual data given significant image change, and the development of an estimation algorithm and data storage structure with bounded computational and storage costs for a fixed map size. Persistent navigation requires the robot to accurately align incoming images against historical data. By its nature, however, visual data contains a high degree of variability despite minimal changes in the scene itself. As a simple example, as the sun moves and weather conditions change, the apparent illumination and shading of objects in the scene can vary significantly. More critically, image alignment must be robust to change in the scene itself, as that change is often a critical output from the robot's re-exploration. This problem is considered in two contexts. First, a set of state-of-the-art feature detection algorithms are evaluated against sample data sets which include both temporally proximal and disparate images of the same location. The capacity of each algorithm to identify repeated point features is measured for a spectrum of algorithm-specific parameter values. Next, the potential of using a prior estimate on the inter-image geometry to improve the robustness of precise image alignment is considered for two phases of the image alignment process: feature matching and robust outlier rejection. A number of geometry-aware algorithms are proposed for both phases, and tested against similar sets of similar and disparate aerial images. While many of the proposed algorithms do improve on the performance of the unguided algorithms, none are vastly superior. The second thread starts by considering the problem of navigation fromdownward-looking aerial images from the perspective of Simultaneous Localization and Mapping (SLAM). This leads to the development of Simultaneous Mosaicking and Resectioning Through Planar Image Graphs (SMARTPIG), an online, iterative mosaicking and SLAM algorithm built on the assumption of a planar scene. A number of samples of SMARTPIG outputs are shown, including mosaics of a 600-meter square airport with approximately 3-meter reprojection errors relative to ground control points. SMARTPIG, like most SLAM algorithms, does not fulfill the criteria for persistent navigation because the computational and storage costs are proportional to the total mission length, not the total area explored. SMARTPIG is evolved towards persistent navigation by the introduction of the featurescape, a storage structure for long-term point-feature data, to produce Planar Image Graphs for PErsistent Navigation (PIGPEN). PIGPEN is demonstrated perfoming robot re-localization onto an existing SMARTPIG mosaic with an accuracy comparable to the original mosaic.

No description available.

Systems that are assembled from independently developed features suffer from feature interactions, in which features affect one another's behaviour in surprising ways. To ensure that a system behaves as intended, developers need to analyze all potential interactions -- and many of the identified interactions need to be fixed and their fixes verified. The feature-interaction problem states that the number of potential interactions to be considered is exponential in the number of features in a system. Resolution strategies combat the feature-interaction problem by offering general strategies that resolve entire classes of interactions, thereby reducing the work of the developer who is charged with the task of resolving interactions. In this thesis, we focus on resolving interactions due to conflict. We present an approach, language, and implementation based on resolver modules modelled in the situation calculus in which the developer can specify an appropriate resolution for each variable under conflict. We performed a case study involving 24 automotive features, and found that the number of resolutions to be specified was much smaller than the number of possible feature interactions (6 resolutions for 24 features), that what constitutes an appropriate resolution strategy is different for different variables, and that the subset of situation calculus we used was sufficient to construct nontrivial resolution strategies for six distinct output variables.

The evolution of technology in the textile industry reached the design of embroidery patterns for machine embroidery. In order to create quality designs the shapes to be embroidered need to be segmented into regions that define different parts. One of the objectives of our research is to develop a method to automatically segment the shapes and by doing so making the process faster and easier. Shape analysis is necessary to find a suitable method for this purpose. It includes the study of different ways to represent shapes. In this thesis we focus on shape representation through its skeleton. We make use of a shape's skeleton and the shape's boundary through the so-called feature transform to decide how to segment a shape and where to place the segment boundaries. The direction of stitches is another important specification in an embroidery design. We develop a technique to select the stitch orientation by defining direction lines using the skeleton curves and information from the boundary. We compute the intersections of segment boundaries and direction lines with the shape boundary for the final definition of the direction line segments. We demonstrate that our shape segmentation technique and the automatic placement of direction lines produce sufficient constrains for automated embroidery designs. We show examples for lettering, basic shapes, as well as simple and complex logos.

An area scan colour camera was used to acquire images of single kernels of Canada Western Red Spring (CWRS) wheat from different growing locations (nine locations in the year 2007, eight locations in the years 2008 and 2009) in Western Canada. Two sample presentation methods were used. In the first method, fifteen kernels from a single location were imaged in a single image and in the second method one kernel from each location were imaged in the same image. Images of individual kernels of barley and rye were also acquired for a classification study. Bulk images of heaped and flat CWRS samples, heaped and flat barley samples, and images of CWRS wheat mixed with different proportion of foreign materials (0%, 2%, 5%, 10%, 20% barley) were acquired. Morphological, colour, and textural features from single kernel images and colour and textural features from bulk grain images were extracted by a program developed by researchers at the Canadian Wheat Board Centre for Grain Storage Research. The top 30 features from the single kernel images of CWRS wheat samples from different growing locations and also different crop years were compared by Scheffe's test. Image features from two types of presentation methods were also compared. Representative of a composite sample which was generated by randomly selecting kernels from each location was compared with individual locations. Three-way classification of CWRS wheat, barley, and rye was done using the top 30 features. For bulk grain image analysis, features from flat bulk grain samples and heaped bulk grain samples were extracted and compared. Image features of CWRS wheat mixed with different percentages of barley were examined, and a cross-validation discriminant classifier was developed to classify CWRS wheat mixed with different percentages of barley. Classifications were also conducted using flat grain as training, flat and heaped grain in testing. Results from this study indicated that most image features from different growing locations and also different crop year samples had significant differences. However, these differences did not influence three-way classification of CWRS wheat, barley, and rye. Features from the composite sample were compared with those from each location. Composite sample features were different from each location. Hence composite samples may not be representative for all locations. However three-way classification using composite sample features gave similar results as in the case of using each location samples. Canada Western Red Spring wheat and barley samples were used in comparing the image features of flat grain and heaped grain. Results indicated that image features from flat grain were different from heaped grain samples. However a two-way classification applied to heaped and flat CWRS wheat, and also heaped and flat barley, gave perfect classification accuracies. Classification models trained using flat grain also gave perfect classification accuracies when tested using flat and heaped grain. A comparison of the top 30 features extracted from images of CWRS wheat mixed with different proportion of barley revealed that grain image features changed after mixing barley. In classification of CWRS wheat mixed with 0, 2, 5, 10, and 20% barley, classification accuracies of 100, 99, 96, 95, and 98% were obtained, respectively.