Bile Ducts Cancer (Cholangiocarcinoma: CCA) is a serious public health problem. The surgical resection is one of the curative treatments for CCA. The surgical resection in the early stage of the CCA gives a good chance for recovery; therefore, early detection in the surgical resection stage is of a critical importance. Periductal fibrosis (PDF) in the bile duct is one factor which is considered about CCA in Thailand. It can be detected using the liver ultrasound images; however, the liver ultrasound images contain speckle noise which decreases PDF detection performance. This paper proposes a new method for enhancement of bile duct ultrasound image (EBDU). The main idea of the EBDU method is to reduce the speckle noise and enhance clear structures of the liver ultrasound images. The proposed method consists of three processes which are the speckle reduction, edge preservation, and intraregion smoothing. The speckle reduction is performed in frequency domain to filter out the high frequency and low frequency noise out of the ultrasound image by using the bandpass filter. The criterion of the bandpass filter is the size of the structures in the ultrasound image, which could be large structures (mirrored edges) and small structures (smoothing). Edge preservation is then performed by applying the statistics filter to distinctly increase the boundary structure; it sorts out all pixel values from the surrounding neighborhood into a numerical order. Finally, intraregions of the liver ultrasound images are smoothed by intra-region smoothing process which can diffuse the homogeneous region. The enhanced liver ultrasound images were tested by computer-aided detection on PDF regions (CADPDF). Variety of liver ultrasound images were used. To evaluate and compare the performance of the proposed method, four measurements are applied which are the scan line pixel (SLP), the Slope-Smooth Speckle Index (SLSI), Equivalent number of looks (ENL), Speckle suppression index (SSI), and the accuracy achieved through the PDF regions segmentation. The experimental results show that the proposed method is able to give higher success rate of enhancing liver ultrasound images compared to other methods. Moreover, the accuracy of CADPDF system was evaluated. The proposed EBDU method and other methods are applied in CADPDF system. The experimental results show that the proposed EBDU method achieved better performance than other methods, giving an accuracy of 80.36%.
Movement artifact direction and magnitude are critical parameters in noise detection and image analysis, especially for single-frame images where temporal information is unavailable. This paper introduces the Movement Artifact Direction Estimation (MADE) algorithm, a signal processing-based approach that performs 3D geometric analysis to estimate both the direction (in degrees) and weighted quantity (in pixels) of movement artifacts. Motivated by computational challenges in medical image quality assessment systems such as LUIAS, this work investigates directional multiplicative noise characterization using controlled experimental conditions with optical camera imaging. The MADE algorithm operates on multi-directional quantification outputs from a preprocessing pipeline—MAPE, ROPE, and MAQ. The methodology is designed for computational efficiency and instantaneous processing, providing interpretable outputs. Experimental results using precision-controlled apparatus demonstrate robust estimation of movement artifact direction and magnitude across a range of image shapes and velocities, with principal outputs aligning closely to ground truth parameters. The proposed MADE algorithm offers a methodological proof of concept for movement artifact analysis in single-frame images, emphasizing both directional accuracy and quantitative assessment under controlled imaging conditions.
Automated optical inspection (AOI) for printed circuit boards (PCBs) requires localizing small, sparse defects under illumination drift and minor placement misalignment, while supporting fast, auditable pass/fail decisions. This paper presents a training-free, reference-based digital image processing framework with no learning/training stage that compares each defective query image with a small library of defect-free reference templates (for the same PCB layout/revision) using a small set of interpretable control parameters. A reference is selected by coarse-to-fine matching (fast pre-screening followed by SSIM refinement on a central region), and an optional global alignment is applied only when it increases SSIM to limit defect-driven over-correction. Defects are highlighted by a defect-likelihood field that fuses an SSIM-derived structural dissimilarity map with a normalized absolute-difference map, followed by connected-component extraction to produce confidence-ranked bounding boxes. The method achieves Precision = 0.9663, Recall = 0.9987, and F1 = 0.9822 at the best-F1 operating point (0.149 false positives per image). Under the adopted box-matching protocol, average precision reaches 0.984. Precision–recall and FROC curves are reported to support threshold selection under different false-alarm budgets.
Motion blur degrades single-frame imaging when relative motion occurs during sensor exposure; yet, quantitative validation is difficult because ground-truth motion parameters are rarely available in real images. This paper presents an interpretable, measure-first framework for detecting, localizing, and quantifying motion blur in single-frame grayscale images under a validated operating condition of one-dimensional horizontal uniform motion. The method analyzes each image row as a one-dimensional spatial signal, where Movement Artifact denotes the scanline-level imprint of motion blur retained in the legacy algorithm names MAPE and MAQ. The pipeline combines three stages: Movement Artifact Position Estimation (MAPE) using scanline self-similarity, Reference Origin Point Estimation (ROPE) using robust structural trends, and Movement Artifact Quantification (MAQ), which summarizes blur magnitude as an average horizontal spatial displacement after adaptive filtering. The pipeline is evaluated on a controlled empirical dataset of 110 images of a high-contrast marker acquired at known tangential velocities from 0.0 to 1.0 m/s in 0.1 m/s increments (10 images per level). MAPE achieves 70–90% detection rates across velocities, and ROPE localizes reference origins with 97–99% detection. An empirical polynomial mapping from MAQ to velocity attains R2 = 0.9900 with RMSE 0.0229 m/s and MAE 0.0221 m/s over 0.0–0.7 m/s, enabling calibrated velocity estimates from blur measurements within the validated regime. An extended additive-noise robustness analysis further shows that severe perturbation can preserve candidate self-similarity responses while progressively destabilizing reference-origin localization and MAQ pairing, thereby clarifying the empirical boundary of the current controlled single-marker regime. The approach is not claimed to generalize to uncontrolled scenes, non-uniform blur, or multi-dimensional and non-rigid motion.