Contour Fitting of Fused Filaments Cross-Section Images by Lemniscates of Booth: Application to Viscous Sintering Kinetics Modeling

A method for image analysis was implemented to determine the edge pixels of two biopolymer-based thermoplastic filaments during their hot melt isothermal sintering at 120 °C. Successive inverted ellipses are adjusted to the contour of the sintered filaments and lead to the identification of the parameters of the corresponding lemniscates of Booth. The different steps of the morphological image analysis are detailed, from 8-bit coded acquired images (1 frame/s), to the final fitting of the optimized mathematical functions describing the evolution of the filaments envelope. The complete sequence is composed of an initial pure viscous sintering step during the first minute, followed by viscoelastic swelling combined with melt spreading for a longer time, and then the stabilization of the sintered filaments shape for over 2 min at high temperatures. Using a master curve obtained from Hopper’s abacus, the characteristic viscous sintering time is assessed at tvs = 78 s, confirming the one previously found based on the measurement of the bonding neck length alone. Then, the full description of the evolution of the thermoplastic filaments envelope is assessable by image analysis during sintering trials as a result of its digital modeling as successive lemniscates of Booth, reflecting geometry changes in the molten state.

Automatic Pectoral Muscle Removal and Microcalcification Localization in Digital Mammograms

Objectives: Breast cancer is the most common cancer diagnosed in women, and microcalcification (MCC) clusters act as an early indicator. Thus, the detection of MCCs plays an important role in diagnosing breast cancer.Methods: This paper presents a methodology for mammogram preprocessing and MCC detection. The preprocessing method employs automatic artefact deletion and pectoral muscle removal based on region-growing segmentation and polynomial contour fitting. The MCC detection method uses a convolutional neural network for region-of-interest (ROI) classification, along with morphological operations and wavelet reconstruction to reduce false positives (FPs).Results: The methodology was evaluated using the mini-MIAS and UTP datasets in terms of segmentation accuracy in the preprocessing phase, as well as sensitivity and the mean FP rate per image in the MCC detection phase. With the mini-MIAS dataset, the proposed methods achieved accuracy scores of 99% for breast segmentation and 95% for pectoral segmentation, a sensitivity score of 82% for MCC detection, and an FP rate per image of 3.27. With the UTP dataset, the methods achieved accuracy scores of 97% for breast segmentation and 91% for pectoral segmentation, a sensitivity score of 78% for MCC detection, and an FP rate per image of 0.74.Conclusions: The proposed preprocessing method outperformed the state-of-the-art methods for breast segmentation and achieved relatively good results for pectoral muscle removal. Furthermore, the MCC detection module achieved the highest test accuracy in identifying potential ROIs with MCCs compared to other methods.

Enhanced diffuse optical tomographic reconstruction using concurrent ultrasound information

Multimodal imaging is an active branch of research as it has the potential to improve common medical imaging techniques. Diffuse optical tomography (DOT) is an example of a low resolution, functional imaging modality that typically has very low resolution due to the ill-posedness of its underlying inverse problem. Combining the functional information of DOT with a high resolution structural imaging modality has been studied widely. In particular, the combination of DOT with ultrasound (US) could serve as a useful tool for clinicians for the formulation of accurate diagnosis of breast lesions. In this paper, we propose a novel method for US-guided DOT reconstruction using a portable time-domain measurement system. B-mode US imaging is used to retrieve morphological information on the probed tissues by means of a semi-automatical segmentation procedure based on active contour fitting. A two-dimensional to three-dimensional extrapolation procedure, based on the concept of distance transform, is then applied to generate a three-dimensional edge-weighting prior for the regularization of DOT. The reconstruction procedure has been tested on experimental data obtained on specifically designed dual-modality silicon phantoms. Results show a substantial quantification improvement upon the application of the implemented technique. This article is part of the theme issue ‘Synergistic tomographic image reconstruction: part 2’.

A Two-Step Phenotypic Parameter Measurement Strategy for Overlapped Grapes under Different Light Conditions

Phenotypic characteristics of fruit particles, such as projection area, can reflect the growth status and physiological changes of grapes. However, complex backgrounds and overlaps always constrain accurate grape border recognition and detection of fruit particles. Therefore, this paper proposes a two-step phenotypic parameter measurement to calculate areas of overlapped grape particles. These two steps contain particle edge detection and contour fitting. For particle edge detection, an improved HED network is introduced. It makes full use of outputs of each convolutional layer, introduces Dice coefficients to original weighted cross-entropy loss function, and applies image pyramids to achieve multi-scale image edge detection. For contour fitting, an iterative least squares ellipse fitting and region growth algorithm is proposed to calculate the area of grapes. Experiments showed that in the edge detection step, compared with current prevalent methods including Canny, HED, and DeepEdge, the improved HED was able to extract the edges of detected fruit particles more clearly, accurately, and efficiently. It could also detect overlapping grape contours more completely. In the shape-fitting step, our method achieved an average error of 1.5% in grape area estimation. Therefore, this study provides convenient means and measures for extraction of grape phenotype characteristics and the grape growth law.

Advanced image analysis of thermoplastic filaments’ viscous sintering kinetics: Contour fitting with a Lemniscate of Booth

Viscous sintering kinetics of thermoplastic polymers has been studied for powders using models refining the Frenkel-Eshelby approach. It is usually based on the measurement of the bonding neck between two molten particles submitted to thermo-microscopy trials. Recently, specific experimental setups have been described for studying the viscous sintering of filaments used in additive manufacturing by FDM. The description of their coalescence by models developed for particles is a rough approximation. However, the evolution of the shape of their section can be modelled by lemniscate curves. In the present work, we present an advanced image analysis approach allowing the fitting of the contour of the filaments by a Lemniscate of Booth. It is based on the automatic assessment of the coordinates of their edge pixels and the adjustment of lemniscates to match their evolving shape as a succession of inverse ellipses. We apply this procedure to a model-biopolymer recently shown as 3D-printable, the plasticized zein, a corn protein extruded as cylindrical filaments. Their sintering is recorded at 120°C as 8-bits coded raw images. After segmentation, a numerical mask is applied to follow the filaments outline. Using Matlab® as computer algebra system, the adjustment and the identification of lemniscates parameters leads to determine the viscous sintering characteristic time, similar to those of standard polymers. Then, the full monitoring of sintering kinetics is achievable and makes possible a better modelling of such experimental trials and their application to enhance the control of the welding between layers in additive manufacturing.

Spherical object recognition based on the number of contour edges extracted by fitting and convex hull processing

The detection of spherical targets in workpiece shape clustering and fruit classification tasks is challenging. Spherical targets produce low detection accuracy in complex fields, and single-feature processing cannot accurately recognize spheres. Therefore, a novel spherical descriptor (SD) for contour fitting and convex hull processing is proposed. The SD achieves image de-noising by combining flooding processing and morphological operations. The number of polygon-fitted edges is obtained by convex hull processing based on contour extraction and fitting, and two RGB images of the same group of objects are obtained from different directions. The two fitted edges of the same target object obtained at two RGB images are extracted to form a two-dimensional array. The target object is defined as a sphere if the two values of the array are greater than a custom threshold. The first classification result is obtained by an improved K-NN algorithm. Circle detection is then performed on the results using improved Hough circle detection. We abbreviate it as a new Hough transform sphere descriptor (HSD). Experiments demonstrate that recognition of spherical objects is obtained with 98.8% accuracy. Therefore, experimental results show that our method is compared with other latest methods, HSD has higher identification accuracy than other methods.

White Blood Cell Image Segmentation Based on Color Component Combination and Contour Fitting

Background: White Blood Cell (WBC) image segmentation plays a key role in cell morphology analysis. However, WBC segmentation is still a challenging task due to the diversity of WBCs under different staining conditions. Objective: In this paper, we propose a novel WBC segmentation method based on color component combination and contour fitting to segment WBC images accurately. Methods: Specifically, the proposed method first uses color component combination and image thresholding to achieve nucleus segmentation, then uses a color prior to remove image background, and extracts the initial WBC contour via Canny edge detection, and finally judges and closes the unclosed WBC contour by contour fitting. Accordingly, cytoplasm segmentation is achieved by subtracting the nucleus region from the WBC region. Results: Experimental results on 100 WBC images under rapid staining condition and 50 WBC images under standard staining condition showed that the proposed method improved segmentation accuracy of white blood cells under rapid and standard staining conditions. Conclusion: The proposed color component combination and contour fitting is effective in WBC segmentation task.

Adaptive 3D Model-Based Facial Expression Synthesis and Pose Frontalization

Facial expressions are one of the important non-verbal ways used to understand human emotions during communication. Thus, acquiring and reproducing facial expressions is helpful in analyzing human emotional states. However, owing to complex and subtle facial muscle movements, facial expression modeling from images with face poses is difficult to achieve. To handle this issue, we present a method for acquiring facial expressions from a non-frontal single photograph using a 3D-aided approach. In addition, we propose a contour-fitting method that improves the modeling accuracy by automatically rearranging 3D contour landmarks corresponding to fixed 2D image landmarks. The acquired facial expression input can be parametrically manipulated to create various facial expressions through a blendshape or expression transfer based on the FACS (Facial Action Coding System). To achieve a realistic facial expression synthesis, we propose an exemplar-texture wrinkle synthesis method that extracts and synthesizes appropriate expression wrinkles according to the target expression. To do so, we constructed a wrinkle table of various facial expressions from 400 people. As one of the applications, we proved that the expression-pose synthesis method is suitable for expression-invariant face recognition through a quantitative evaluation, and showed the effectiveness based on a qualitative evaluation. We expect our system to be a benefit to various fields such as face recognition, HCI, and data augmentation for deep learning.

Image recognition and diagnosis for vibration characteristics of cone valve core

Research on vibration characteristics of hydraulic valves is helpful to improve the performance of the hydraulic valve. In this article, a visualization experimental method is designed to capture the cone valve core vibration, and the image sequence of the vibration is obtained. And the least-squares contour fitting of the valve core is proposed to analyze the vibration characteristics of the valve core, which could eliminate noise in the vibration signal and improve accuracy. The difference of the least-squares variance between adjacent data points obtained by least-squares contour fitting is one order of magnitude smaller than corner detection method, while the signal-to-noise ratio is more than twice the corner detection. Furthermore, the frequency spectrum and amplitude of the valve core vibration are also discussed. The deviation of the valve core from the coordinate origin will increase with increasing of the pressure difference and decreasing of the pre-compression of the spring and the amplitude of vibration increases too. The vibration signal of the valve core under different conditions has similar frequency spectrum, which is mainly composed of the vibration signal spectrum caused by the fluctuation of oil pressure and turbulence of the liquid system.