Topological hierarchy-contour tracing algorithm for nests of interconnected contours

As a simple meaningful external illustration, a group of boundary contours is commonly used for representing the physical appearance of an object of interest on a 2D plane (e.g., a part drawing, CT scan image, a sliced layer, tile pattern). The illustration is understood from the composition of the contours and their attributes that include their shapes, sizes, locations and relationships. Therefore, not only is geometrical information important for contours to be useful in subsequent operations but their topological hierarchy relationships also are essential. Presented in this paper is a topological hierarchy-contour tracing algorithm that is capable of tracing nests of interconnected contours often found in practice and of identifying their topological hierarchy relationships automatically during contour tracing. The algorithm organizes contours by family rather than by group or as individual. However, contours are traced across families generation by generation instead of going deep with one family branch at a time. The outputs of the algorithm are ordered sequences of boundary pixels representing all closed contours and their topological hierarchy relationships. The algorithm has been implemented on LabVIEW, and tested with several samples to illustrate its applications.     

Automatic single-line drawing creation from a paper-based overtraced freehand sketch

Freehand sketching on a paper is commonly found to be used as it is a natural and intuitive communication channel for portraying ideas. Additional strokes are often drawn over the existing ones to make the sketch clearer. For its usefulness in subsequent steps, a sketch is transformed to be a 3D CAD model that is typically performed manually by a designer due to a lack of technology support. Geometrical reconstruction from an offline scanning of a sketch has been a challenge because enriched information obtained during sketching is reduced to a batch of data points. This paper presents an algorithm for identifying a single-line drawing from a paper-based overtraced sketch as it is the first important step towards geometrical reconstruction. Key activities in this approach are thick-line sketch creation, contour boundary extraction, segments identification, and line drawing creation. The algorithm has been successfully implemented on LabVIEW and tested with several samples.     

Enhance Egocentric Grasp Recognition Based Flex Sensor Under Low Illumination

Egocentric recognition is exciting computer vision research by acquiring images and video from the first-person overview. However, an image becomes noisy and dark under low illumination conditions, making subsequent hand detection tasks difficult. Thus, image enhancement is necessary to make buried detail more visible. This article addresses the challenge of egocentric hand grasp recognition in low light conditions by utilizing the flex sensor and image enhancement algorithm based on adaptive gamma correction with weighting distribution. Initially, a flex sensor is installed to the thumb for object manipulation. The thumb placement that holds in a different position on the object of each grasp affects the voltage changing of the flex sensor circuit. The average voltages are used to configure the weighting parameter to improve images in the image enhancement stage. Moreover, the contrast and gamma function are used to adjust varies the low light condition. These grasp images are then separated to be training and testing with pre-trained deep neural networks as the feature extractor in YOLOv2 detection network for the grasp recognition system. The proposed of using a flex sensor significantly improves the grasp recognition rate in low light conditions.     

Spray coating thin polymeric sensor films for Au3+

A novel polymeric sensor of the poly(sodium-4-styrenesulfonate) (PSS)-modified rhodamine B derivative (Rho) was synthesized using 1-ethyl-3-(3-dimethylaminopropyl)carbodiimide (EDC)/N,N′-dimethylpyridin-4-amine (DMAP) as coupling reagents to obtain PSS-Rho4 in 21% yield. The characterization and “Off–On” sensing phenomena were established through UV–Vis, fluorescence, NMR, and FTIR techniques. The PSS-Rho4 showed high selectivity and sensitivity for Au³⁺ over other metal ions. Upon the addition of Au³⁺, significant color change and “Off–On” fluorescence were observed due to a cation Au³⁺ induced spirolactam ring-opening process with detection limit down to micromolar values (1.2 μM). In addition, spray coating thin polymeric sensor films were produced onto the surface of material (PSS-Rho4-ITO and PSS-Rho4-filtered paper) providing a fast, portable, and easy-to-use molecular device for the detection of Au³⁺ in the real system. Reversibility was evaluated by rinsing with EDTA solution under basic condition. We believe that, this approach provides a sensitive and accurate method for the detection of Au³⁺ in environmental and biological applications. © 2019 Wiley Periodicals, Inc. J. Appl. Polym. Sci. 2020 , 137, 48273.     

A new algorithm for tracing nests of interconnected contours

Boundary contour, a meaningful external representation of area of interest, is widely used in many manufacturing applications (e.g., part machining, rapid prototyping, cutting and packing of irregular shape patterns, and geometrical reconstruction), and appearing on an image, in many cases, are nests of interconnected contours that their information is typically required prior to subsequent manufacturing operations being performed. Presented in this paper is a new contour tracing algorithm for extracting nests of interconnected contours. The algorithm is capable of recognizing junctions between contours sharing common edges and of recommending, among alternatives, a path to proceed to obtain all interconnected contours. Morphological operations have been applied instead of component labeling to achieve the locations of nested contours on an image. The input to the algorithm is a binary image of 1-pixel-wide closed contours, and the outputs are ordered sequences of boundary pixels representing all closed contours. The algorithm has been implemented on LabVIEW, experimented with several contour patterns, and demonstrated its application in manufacturing.