A novel plant type, leaf disease and severity identification framework using CNN and transformer with multi-label method.

The growth of plants is threatened by numerous diseases. Accurate and timely identification of these diseases is crucial to prevent disease spreading. Many deep learning-based methods have been proposed for identifying leaf diseases. However, these methods often combine plant, leaf disease, and severity into one category or treat them separately, resulting in a large number of categories or complex network structures. Given this, this paper proposes a novel leaf disease identification network (LDI-NET) using a multi-label method. It is quite special because it can identify plant type, leaf disease and severity simultaneously using a single straightforward branch model without increasing the number of categories and avoiding extra branches. It consists of three modules, i.e., a feature tokenizer module, a token encoder module and a multi-label decoder module. The LDI-NET works as follows: Firstly, the feature tokenizer module is designed to enhance the capability of extracting local and long-range global contextual features by leveraging the strengths of convolutional neural networks and transformers. Secondly, the token encoder module is utilized to obtain context-rich tokens that can establish relationships among the plant, leaf disease and severity. Thirdly, the multi-label decoder module combined with a residual structure is utilized to fuse shallow and deep contextual features for better utilization of different-level features. This allows the identification of plant type, leaf disease, and severity simultaneously. Experiments show that the proposed LDI-NET outperforms the prevalent methods using the publicly available AI challenger 2018 dataset.

A method for demand-accurate one-dimensional cutting problems with pattern reduction.

The main objective in the one-dimensional cutting stock problem (1D-CSP) is to minimize material costs. In practice, it is useful to focus on auxiliary objectives, one of which is to reduce the number of different cutting patterns. This paper discusses the classical integer IDCSP, where only one type of stock object is included. Meanwhile, the demands of various items must be precisely satisfied in the constraints. In other words, no overproduction or underproduction is allowed. Therefore, to solve this issue, a variable-to-constant method based on a new mathematical model is proposed. In addition, we integrate the approach with two other representative methods to demonstrate its effectiveness. Both benchmark instances and real instances are used in the experiments, and the results show that the methodology is effective in reducing patterns. In particular, in terms of the solutions to the real-life instances, the proposed approach presents a 31.93 to 37.6% pattern reduction compared to other similar methods (including commercial software).

Feature Pyramid Nonlocal Network With Transform Modal Ensemble Learning for Breast Tumor Segmentation in Ultrasound Images.

Automated breast ultrasound image segmentation is essential in a computer-aided diagnosis (CAD) system for breast tumors. In this article, we present a feature pyramid nonlocal network (FPNN) with transform modal ensemble learning (TMEL) for accurate breast tumor segmentation in ultrasound images. Specifically, the FPNN fuses multilevel features under special consideration of long-range dependencies by combining the nonlocal module and feature pyramid network. Additionally, the TMEL is introduced to guide two iFPNNs to extract different tumor details. Two publicly available datasets, i.e., the Dataset-Cairo University and Dataset-Merge, were used for evaluation. The proposed FPNN-TMEL achieves a Dice score of 84.70% ± 0.53%, Jaccard Index (Jac) of 78.10% ± 0.48% and Hausdorff distance (HD) of 2.815 ± 0.016 mm on the Dataset-Cairo University, and Dice of 87.00% ± 0.41%, Jac of 79.16% ± 0.56%, and HD of 2.781±0.035 mm on the Dataset-Merge. Qualitative and quantitative experiments show that our method outperforms other state-of-the-art methods for breast tumor segmentation in ultrasound images. Our code is available at https://github.com/pixixiaonaogou/FPNN-TMEL.

Defect detection in code characters with complex backgrounds based on BBE.

Computer vision technologies have been widely implemented in the defect detection. However, most of the existing detection methods generally require images with high quality, and they can only process code characters on simple backgrounds with high contrast. In this paper, a defect detection approach based on deep learning has been proposed to efficiently perform defect detection of code characters on complex backgrounds with a high accuracy. Specifically, image processing algorithms and data enhancement techniques were utilized to generate a large number of defect samples to construct a large data set featuring a balanced positive and negative sample ratio. The object detection network called BBE was build based on the core module of EfficientNet. Experimental results show that the mAP of the model and the accuracy reach 0.9961 and 0.9985, respectively. Individual character detection results were screened by setting relevant quality inspection standards to evaluate the overall quality of the code characters, the results of which have verified the effectiveness of the proposed method for industrial production. Its accuracy and speed are high with high robustness and transferability to other similar defect detection tasks. To the best of our knowledge, this report describes the first time that the BBE has been applied to defect inspections for real plastic container industry.

GP-CNN-DTEL: Global-Part CNN Model With Data-Transformed Ensemble Learning for Skin Lesion Classification.

Precise skin lesion classification is still challenging due to two problems, i.e., (1) inter-class similarity and intra-class variation of skin lesion images, and (2) the weak generalization ability of single Deep Convolutional Neural Network trained with limited data. Therefore, we propose a Global-Part Convolutional Neural Network (GP-CNN) model, which treats the fine-grained local information and global context information with equal importance. The Global-Part model consists of a Global Convolutional Neural Network (G-CNN) and a Part Convolutional Neural Network (P-CNN). Specifically, the G-CNN is trained with downscaled dermoscopy images, and is used to extract the global-scale information of dermoscopy images and produce the Classification Activation Map (CAM). While the P-CNN is trained with the CAM guided cropped image patches and is used to capture local-scale information of skin lesion regions. Additionally, we present a data-transformed ensemble learning strategy, which can further boost the classification performance by integrating the different discriminant information from GP-CNNs that are trained with original images, color constancy transformed images, and feature saliency transformed images, respectively. The proposed method is evaluated on the ISIC 2016 and ISIC 2017 Skin Lesion Challenge (SLC) classification datasets. Experimental results indicate that the proposed method can achieve the state-of-the-art skin lesion classification performance (i.e., an AP value of 0.718 on the ISIC 2016 SLC dataset and an Average Auc value of 0.926 on the ISIC 2017 SLC dataset) without any external data, compared with other current methods which need to use external data.

AMC-Net: Asymmetric and multi-scale convolutional neural network for multi-label HPA classification.

BACKGROUND AND OBJECTIVES: The multi-label Human Protein Atlas (HPA) classification can yield a better understanding of human diseases and help doctors to enhance the automatic analysis of biomedical images. The existing automatic protein recognition methods have been limited to single pattern. Therefore, an automatic multi-label human protein atlas recognition system with satisfactory performance should be conducted. This work aims to build an automatic recognition system for multi-label human protein atlas classification based on deep learning. METHODS: In this work, an automatic feature extraction and multi-label classification framework is proposed. Specifically, an asymmetric and multi-scale convolutional neural network is designed for HPA classification. Furthermore, this work introduces a combined loss that consists of the binary cross-entropy and F1-score losses to improve identification performance. RESULTS: Rigorous experiments are conducted to estimate the proposed system. In particular, unlike the current automatic identification systems, which focus on a limited number of patterns, the proposed method is capable of classifying mixed patterns of proteins in microscope images and can handle the subcellular multi-label protein classification task including 28 subcellular localization patterns. The proposed framework based on deep convolutional neural network outperformed the existing approaches with a F1-score of 0.823, which illustrates the robustness and effectiveness of the proposed system. CONCLUSION: This study proposed a high-performance recognition system for protein atlas classification based on deep learning, and it achieved an automatic multi-label human protein atlas identification framework with superior performance than previous studies.

Efficient skin lesion segmentation using separable-Unet with stochastic weight averaging.

BACKGROUND AND OBJECTIVE: Efficient segmentation of skin lesion in dermoscopy images can improve the classification accuracy of skin diseases, which provides a powerful approach for the dermatologists in examining pigmented skin lesions. However, the segmentation is challenging due to the low contrast of skin lesions from a captured image, fuzzy and indistinct lesion boundaries, huge variety of interclass variation of melanomas, the existence of artifacts, etc. In this work, an efficient and accurate melanoma region segmentation method is proposed for computer-aided diagnostic systems. METHOD: A skin lesion segmentation (SLS) method based on the separable-Unet with stochastic weight averaging is proposed in this work. Specifically, the proposed Separable-Unet framework takes advantage of the separable convolutional block and U-Net architectures, which can extremely capture the context feature channel correlation and higher semantic feature information to enhance the pixel-level discriminative representation capability of fully convolutional networks (FCN). Further, considering that the over-fitting is a local optimum (or sub-optimum) problem, a scheme based on stochastic weight averaging is introduced, which can obtain much broader optimum and better generalization. RESULTS: The proposed method is evaluated in three publicly available datasets. The experimental results showed that the proposed approach segmented the skin lesions with an average Dice coefficient of 93.03% and Jaccard index of 89.25% for the International Skin Imaging Collaboration (ISIC) 2016 Skin Lesion Challenge (SLC) dataset, 86.93% and 79.26% for the ISIC 2017 SLC, and 94.13% and 89.40% for the PH2 dataset, respectively. The proposed approach is compared with other state-of-the-art methods, and the results demonstrate that the proposed approach outperforms them for SLS on both melanoma and non-melanoma cases. Segmentation of a potential lesion with the proposed approach in a dermoscopy image requires less than 0.05 s of processing time, which is roughly 30 times faster than the second best method (regarding the value of Jaccard index) for the ISIC 2017 dataset with the same hardware configuration. CONCLUSIONS: We concluded that using the separable convolutional block and U-Net architectures with stochastic weight averaging strategy could enable to obtain better pixel-level discriminative representation capability. Moreover, the considerably decreased computation time suggests that the proposed approach has potential for practical computer-aided diagnose systems, besides provides a segmentation for the specific analysis with improved segmentation performance.

Multi-proportion channel ensemble model for retinal vessel segmentation.

OBJECTIVE: A novel supervised method that is based on the Multi-Proportion Channel Ensemble Model (MPC-EM) is proposed to obtain more vessel details with reduced computational complexity. METHODS: Existing Retinal Vessel Segmentation (RVS) algorithms only work using the single G channel (Green Channel) of fundus images because that channel normally contains the most details with the least noise, while the red and blue channels are usually saturated and noisy. However, we find that the images that are composed of the αG-channel and (1-α) R-channel (Red Channel) with different values of α produce multiple particular global features. This enables the model to detect more local vessel details in fundus images. Therefore, we provide a detailed description and evaluation of the segmentation approach based on the MPC-EM for the RVS. The segmentation approach consists of five identical submodels. Each submodel can capture various vessel details by being trained using different composition images. These probabilistic maps that are produced by five submodels are averaged to achieve the final refined segmentation results. RESULTS: The proposed approach is evaluated using 4 well-established datasets, i.e., DRIVE, STARE, HRF and CHASE_DB1, with accuracies of 95.74%, 96.95%, 96.31%, and 96.54%, respectively. Additionally, quantitative comparisons with other existing methods and cross-training results are included. CONCLUSION: The segmentation results showed that the proposed algorithm based on the MPC-EM with simple submodels can achieve state-of-the-art accuracy with reduced computational complexity. SIGNIFICANCE: Compared with other existing methods that are trained using only the G channel and raw images, the proposed approach based on the MPC-EM, submodels of which are trained using different proportional compositions of R and G channels, obtains better segmentation accuracy and robustness. Additionally, the experimental results show that the R channel of fundus images can also produce performance gains for RVS.

Weakly Supervised Biomedical Image Segmentation by Reiterative Learning.

Recent advances in deep learning have produced encouraging results for biomedical image segmentation; however, outcomes rely heavily on comprehensive annotation. In this paper, we propose a neural network architecture and a new algorithm, known as overlapped region forecast, for the automatic segmentation of gastric cancer images. To the best of our knowledge, this report for the first time describes that deep learning has been applied to the segmentation of gastric cancer images. Moreover, a reiterative learning framework that achieves superior performance without pretraining or further manual annotation is presented to train a simple network on weakly annotated biomedical images. We customize the loss function to make the model converge faster while avoiding becoming trapped in local minima. Patch boundary errors were eliminated by our overlapped region forecast algorithm. By studying the characteristics of the model trained using two different patch extraction methods, we train iteratively and integrate predictions and weak annotations to improve the quality of the training data. Using these methods, a mean Intersection over Union coefficient of 0.883 and a mean accuracy of 91.09% were achieved on the partially labeled dataset, thereby securing a win in the 2017 China Big Data and Artificial Intelligence Innovation and Entrepreneurship Competition.

Methods and Research for Multi-Component Cutting Force Sensing Devices and Approaches in Machining.

Multi-component cutting force sensing systems in manufacturing processes applied to cutting tools are gradually becoming the most significant monitoring indicator. Their signals have been extensively applied to evaluate the machinability of workpiece materials, predict cutter breakage, estimate cutting tool wear, control machine tool chatter, determine stable machining parameters, and improve surface finish. Robust and effective sensing systems with capability of monitoring the cutting force in machine operations in real time are crucial for realizing the full potential of cutting capabilities of computer numerically controlled (CNC) tools. The main objective of this paper is to present a brief review of the existing achievements in the field of multi-component cutting force sensing systems in modern manufacturing.

Modular design and development methodology for robotic multi-axis F/M sensors.

Accurate Force/Moment (F/M) measurements are required in many applications, and multi-axis F/M sensors have been utilized a wide variety of robotic systems since 1970s. A multi-axis F/M sensor is capable of measuring multiple components of force terms along x-, y-, z-axis (Fx, Fy, Fz), and the moments terms about x-, y- and z-axis (Mx, My and Mz) simultaneously. In this manuscript, we describe experimental and theoretical approaches for using modular Elastic Elements (EE) to efficiently achieve multi-axis, high-performance F/M sensors. Specifically, the proposed approach employs combinations of simple modular elements (e.g. lamella and diaphragm) in monolithic constructions to develop various multi-axis F/M sensors. Models of multi-axis F/M sensors are established, and the experimental results indicate that the new approach could be widely used for development of multi-axis F/M sensors for many other different applications.

Design and Analysis of a Sensor System for Cutting Force Measurement in Machining Processes.

Multi-component force sensors have infiltrated a wide variety of automation products since the 1970s. However, one seldom finds full-component sensor systems available in the market for cutting force measurement in machine processes. In this paper, a new six-component sensor system with a compact monolithic elastic element (EE) is designed and developed to detect the tangential cutting forces Fx, Fy and Fz (i.e., forces along x-, y-, and z-axis) as well as the cutting moments Mx, My and Mz (i.e., moments about x-, y-, and z-axis) simultaneously. Optimal structural parameters of the EE are carefully designed via simulation-driven optimization. Moreover, a prototype sensor system is fabricated, which is applied to a 5-axis parallel kinematic machining center. Calibration experimental results demonstrate that the system is capable of measuring cutting forces and moments with good linearity while minimizing coupling error. Both the Finite Element Analysis (FEA) and calibration experimental studies validate the high performance of the proposed sensor system that is expected to be adopted into machining processes.