In this paper, we examine and research the effect of long skip connection on convolutional neural networks (CNNs) for the tasks of image (surface defect) classification. The standard popular models only apply short skip connection inside blocks (layers with the same size). We apply the long version of residual connection on several proposed models, which aims to reuse the lost spatial knowledge from the layers close to input. For some models, Depthwise Separable Convolution is used rather than traditional convolution in order to reduce both count of parameters and floating-point operations per second (FLOPs). Comparative experiments of the newly upgraded models and some popular models have been carried out on different datasets including Bamboo strips datasets and a reduced version of ImageNet. The modified version of DenseNet 121 (we call MDenseNet 121) achieves higher validation accuracy while it has about 75% of weights and FLOPs in comparison to the original DenseNet 121.

Laser interferometers can achieve a nanometer-order uncertainty of measurements when their frequencies are locked to the reference frequencies of the atom or molecule transitions. There are three types of displacement-measuring interferometers: homodyne, heterodyne, and frequency modulation (FM) interferometers. Among these types of interferometer, the FM interferometer has many advantageous features. The interference signal is a series of time-dependent harmonics of modulation frequency, so the phase shift can be detected accurately using the synchronous detection method. Moreover, the FM interferometer is the most suitable for combination with a frequency-locked laser because both require frequency modulation. In previous research, low modulation frequencies at some tens of kHz have been used to lock the frequency of laser diodes (LDs). The low modulation frequency for the laser source means that the maximum measurement speed of the FM interferometers is limited. This paper proposes a novel contribution regarding the application of a high-frequency modulation for an LD to improve both the frequency stability of the laser source and the measurement speed of the FM interferometer. The frequency of the LD was locked to an I₂ hyperfine component at 1 MHz modulation frequency. A high bandwidth lock-in amplifier was utilized to detect the saturated absorption signals of the I₂ hyperfine structure and induce the signal to lock the frequency of the LD. The locked LD was then used for an FM displacement measuring interferometer. Moreover, a suitable modulation amplitude that affected the signal-to-noise ratio of both the I₂ absorption signal and the harmonic intensity of the interference signal was determined. In order to verify the measurement resolution of the proposed interferometer, the displacement induced by a piezo electric actuator was concurrently measured by the interferometer and a capacitive sensor. The difference of the displacement results was less than 20 nm. To evaluate the measurement speed, the interferometer was used to measure the axial error of a high-speed spindle at 500 rpm. The main conclusion of this study is that a stable displacement interferometer with high accuracy and a high measurement speed can be achieved using an LD frequency locked to an I₂ hyperfine transition at a high modulation frequency.

This paper proposes a machine vision system for the surface inspection of black rubber rollers in manufacturing processes. The system aims to enhance the surface quality of the rollers by detecting and classifying defects. A lighting system is installed to highlight surface defects. Two algorithms are proposed for defect detection: a traditional-based method and a deep learning-based method. The former is fast but limited to surface defect detection, while the latter is slower but capable of detecting and classifying defects. The accuracy of the algorithms is verified through experiments, with the traditional-based method achieving near-perfect accuracy of approximately 98% for defect detection, and the deep learning-based method achieving an accuracy of approximately 95.2% for defect detection and 96% for defect classification. The proposed machine vision system can significantly improve the surface inspection of black rubber rollers, thereby ensuring high-quality production.

With the rapid development of cameras and deep learning technologies, computer vision tasks such as object detection, object segmentation and object tracking are being widely applied in many fields of life. For robot grasping tasks, object segmentation aims to classify and localize objects, which helps robots to be able to pick objects accurately. The state-of-the-art instance segmentation network framework, Mask Region-Convolution Neural Network (Mask R-CNN), does not always perform an excellent accurate segmentation at the edge or border of objects. The approach using 3D camera, however, is able to extract the entire (foreground) objects easily but can be difficult or require a large amount of computation effort to classify it. We propose a novel approach, in which we combine Mask R-CNN with 3D algorithms by adding a 3D process branch for instance segmentation. Both outcomes of two branches are contemporaneously used to classify the pixels at the edge objects by dealing with the spatial relationship between edge region and mask region. We analyze the effectiveness of the method by testing with harsh cases of object positions, for example, objects are closed, overlapped or obscured by each other to focus on edge and border segmentation. Our proposed method is about 4 to 7% higher and more stable in IoU (intersection of union). This leads to a reach of 46% of mAP (mean Average Precision), which is a higher accuracy than its counterpart. The feasibility experiment shows that our method could be a remarkable promoting for the research of the grasping robot.

Cranial reconstruction is a critical task in computer-assisted surgery, requiring both high geometric accuracy and computational efficiency for patient-specific implant design. While recent deep learning approaches, particularly 3D UNet-based models, have demonstrated promising performance, most studies primarily focus on architectural modifications, with limited attention to the systematic impact of data preparation and training strategies on reconstruction quality. In this study, we present a comprehensive data-centric investigation of key factors influencing the performance of a baseline 3D UNet for cranial defect reconstruction. Specifically, we analyze the effects of data preprocessing (denoising), dataset organization (ordered versus randomized training), defect morphology diversity, convolutional kernel size, and loss function design under controlled experimental conditions. Experiments were conducted on 250 complete skulls (NRRD format) from the MUG500+ dataset, with synthetically generated defects across multiple anatomical regions. From these volumes, a total of 3750 training samples were generated, including: (i) 1250 noisy samples with diverse defect morphologies, (ii) 1250 denoised samples with ellipsoidal defects, and (iii) 1250 denoised samples with multiple defect types. The results demonstrate that data-centric and training-related factors have a substantial impact on model performance, in several cases exceeding the influence of architectural design. In particular, denoising significantly improves boundary stability and reduces geometric error, while incorporating diverse defect morphologies enhances generalization to unseen shapes. Additionally, ordered training contributes to more stable convergence, and an optimal kernel size of (3 × 3 × 3) achieves the best trade-off between accuracy and computational efficiency. A hybrid Dice and boundary loss further improves boundary precision compared to conventional Dice loss. The optimized configuration achieves a Dice Similarity Coefficient of 0.94 and a Hausdorff Distance of 3.8 mm, with an average inference time of 0.004 s per case. These results demonstrate that data-centric optimization can be as influential as, or even more impactful than, architectural design in cranial defect reconstruction. The findings provide practical and reproducible guidelines for developing efficient, robust, and clinically applicable deep learning-based systems for patient-specific cranial implant design.