Quality Control Tasks Research Articles

Hardware Design Strategies Oriented to Edge Computing and AgriFood Electronics for Image Processing using Cellular Automata

There has been a growing interest from academia and industry in developing circuits and systems for edge computing and quality control tasks in food production lines, where image-processing is frequently required. This paper outlines the required considerations for designing a fruit classification system based on image-processing using Cellular Automata (CA) models and integrating it into reconfigurable hardware (HW) such as Field Programmable Gate Arrays (FPGAs). Parallel processing in CA requires numerous processing elements to be implemented and mapping CA models to HW generally comes with limitations. Homogeneous CA arrays are easier to design and implement in HW but can be resource-demanding. To fill this gap, this study explores different alternatives for the HW implementation of CA models, particularly trading computational-parallelism for a more optimized use of the available HW resources. We conducted experimental tests of the designed HW system using the Digilent Nexys development board, and the operation was validated against software-based benchmarks for image-processing, particularly concerning edge-detection. The presented study provides a broader range of design solutions for the HW implementation of two-dimensional CA models and a better understanding of their advantages and disadvantages. The results show that solutions focusing on instruction-parallelism add some complexity to the conception and require more design effort, compared to homogeneous CA models composed of identical cells. However, the instruction-parallel design solutions can significantly improve the HW resource utilization, especially when implementing computationally intensive CA rules in FPGAs.

Deep learning of 3D point clouds for detecting geometric defects in gears

Geometric integrity directly impacts the functionality, reliability, and safety of final manufactured products, making the qualification of parts based on measurements of their geometry a fundamental quality control activity in modern manufacturing. Recent advancements in three-dimensional (3D) metrology technologies have enabled fine-scale inspection of geometric integrity characterized by dimensional accuracy, surface quality, and shape conformity. However, the widespread adoption of high-resolution 3D metrology in manufacturing faces some significant challenges posed by the inherent data structures of 3D point clouds such as high dimensionality, unstructured nature, and sparsity in defective regions. To address these challenges, this paper first creates a “MFGNet-gear” dataset, which is a scalable and comprehensive benchmark dataset comprising 12 part designs with four quality classes for each design. Subsequently, we develop a deep learning model adapted from the PointNet++ architecture to enable automated, end-to-end analysis of 3D point clouds. The model can be configured for different decision-making tasks including part design classification and multi-class geometric defect detection. Implementations of the proposed model on the “MFGNet-gear” dataset achieve accuracies up to 100% in classifying gear designs and up to 85% in four-class quality inspection. Additionally, we systematically investigate the impacts of measurement resolution and precision on the classification performance through a series of case studies. The obtained results highlight the potential of using deep learning methods for automated analysis of 3D point clouds for a variety of quality control tasks beyond gear manufacturing. This study also proposes future research directions, including the development of new deep learning architectures specifically designed for manufacturing 3D point clouds and strategies for adaptive measurement planning.

Raman Spectroscopic Analysis of Steviol Glycosides: Spectral Database and Quality Control Algorithms

Besides all sharing an extraordinary high (i.e., up to ~450 times) sweetening power as compared to sucrose and while presenting strong similarities in their molecular structures, molecules belonging to the family of diterpene glycosides (i.e., the secondary metabolites of Stevia rebaudiana) differ in specific structural details that strongly impact on their levels of sweetness and bitter aftertaste. Given the nutritional and pharmacological benefits of steviol secondary metabolites as natural dietetic and anti-diabetic remedies, extraction and purification of steviol glycosides from plant material are nowadays widely spread among many countries. However, an unpleasant bitter aftertaste, which is linked to a genetic variation in human bitter taste receptors, hampers the full exploitation of such benefits and calls for a prompt improvement in organoleptic property control of stevia products. A deeper understanding of the molecular structure of different steviol glycosides and the consequent development of promptly measurable criteria for the organoleptic performance of their mixtures will support processing optimization and control of taste profiles within desired yields. The present research aimed at establishing Raman spectroscopic algorithms for quantitative characterizations of raw stevia-based sweetener products. First, a series of twelve high-purity diterpene glycosides were analyzed by high spectrally resolved Raman spectroscopy and their spectra analyzed in order to establish a complete Raman library of molecular structures. Then, quantitative spectroscopic parameters were built up and applied to characterize the organoleptic property of five different commercially available samples including the recently developed Rebaudioside M isoform. Raman spectroscopy was confirmed as a versatile analytical technique that could be used for quantitative quality control tasks on the production line and for prompt in situ characterizations of purchased products.

Artificial Intelligence‐Driven Smart Scan: A Rapid, Automatic Approach for Comprehensive Imaging and Spectroscopy for Fast Compositional Analysis

Nanomaterial properties and functionalities are influenced by their shape, size, and chemical composition. The importance of these parameters highlights the need for a statistically robust analysis of a large particle population, necessitating automation. This study introduces a neural network‐empowered smart scan technique that achieves a relative increase in speed compared to traditional energy‐dispersive X‐ray spectroscopy (EDX) mapping. The main advantage is that it reduces the required dose, decreasing potential damage to the sample by avoiding unnecessary exposure. It holds potential use in other multimodal scanning transmission electron microscopy or scanning‐based imaging approaches. In the first example, identifying particles in a matrix with a trained neural network reduces the acquisition time by two orders of magnitude. This acceleration enables a statistical compositional analysis of thousands of particles in less than 1 h. Similar improvements are observed for atomic resolution. The discrete positions of atoms identified by the trained network allow for selective EDX sampling at these centers, thereby identifying the atomic species of the column with much‐reduced sampling. Consequently, a lower sampling dose is required, enabling mapping of more delicate materials with high lateral resolution and at a high statistical confidence interval. Even though manual training is still required, this approach greatly benefits repetitive quality control tasks.

QRATER: a collaborative and centralized imaging quality control web-based application

Quality control (QC) is an important part of all scientific analyses, including neuroscience. With manual curation considered the gold standard, there remains a lack of available tools that make manual neuroimaging QC accessible, fast, and easy. In this article we present Qrater, a containerized web-based Python application that enables viewing and rating any type of image for QC purposes. Qrater functionalities allow collaboration between various raters on the same dataset which can facilitate completing large QC tasks. Qrater was used to evaluate QC rater performance on three different magnetic resonance (MR) image QC tasks by a group of raters having different amounts of experience. The tasks included QC of raw MR images (10,196 images), QC of linear registration to a standard template (10,196 images), and QC of skull segmentation (6,968 images). We measured the proportion of failed images, average rating time per image, intra- and inter-rater agreement, as well as the comparison against QC using a conventional method. The median time spent rating per image differed significantly between raters (depending on rater experience) in each of the three QC tasks. Evaluating raw MR images was slightly faster using Qrater than an image viewer (expert: 99 vs. 90 images in 63 min; trainee 99 vs 79 images in 98 min). Reviewing the linear registration using Qrater was twice faster for the expert (99 vs. 43 images in 36 min) and three times faster for the trainee (99 vs. 30 images in 37 min). The greatest difference in rating speed resulted from the skull segmentation task where the expert took a full minute to inspect the volume on a slice-by-slice basis compared to just 3 s using Qrater. Rating agreement also depended on the experience of the raters and the task at hand: trained raters’ inter-rater agreements with the expert’s gold standard were moderate for both raw images (Fleiss’ Kappa = 0.44) and linear registration (Fleiss’ Kappa = 0.56); the experts’ inter-rater agreement of the skull segmentation task was excellent (Cohen’s Kappa = 0.83). These results demonstrate that Qrater is a useful asset for QC tasks that rely on manual evaluation of QC images.

Quality-centered production and maintenance scheduling for multi-machine manufacturing systems under variable operating conditions

Production, maintenance, and quality represent the three primary tasks in manufacturing systems. Previous studies have predominantly focused on optimizing these tasks separately or jointly optimizing two of them. However, it is worth noting that these tasks exhibit mutual interaction, and models failing to consider them simultaneously cannot achieve global optimality. Therefore, this paper aims to develop a quality-centered production and maintenance scheduling methodology (QPMSM) for multi-machine and multi-product manufacturing systems. Specifically, a delivery time-based production scheduling strategy is introduced to emphasize the impact of maintenance activities. A quality loss model is developed to characterize the mapping relationship between quality deterioration and component degradation. Furthermore, a well-designed maintenance strategy determines the optimal timing and frequency of maintenance activities to improve system performance and reduce quality deterioration. Building upon this foundation, an integrated model is proposed to concurrently optimize production scheduling, maintenance planning, and quality control tasks to minimize the overall system cost. The effectiveness of the proposed QPMSM in terms of cost-savings has been verified using a designed hybrid meta-heuristic algorithm, providing a viable approach for simultaneous optimization.

SISTEM INFORMASI PENCATATAN PRODUKSI PAKAIAN BERBASIS ANDROID

CV. Aya Sofya is a Muslim clothing manufacturer specializing in Gamis, Baju Koko, Kemeja Koko, Jilbab, Mukena, skirts, Civil Servant Office Uniforms, and more. Recognizing the need for efficiency, the company implemented an Android and web-based Information System. This system, developed with native Android and Codeigniter framework, streamlines quality control, warehouse operations, and administrative tasks. Following the System Development Life Cycle with the Waterfall model, and aided by Unified Modeling Language (UML), the manual production recording process has been replaced, significantly enhancing effectiveness and efficiency. The frontend on Android allows quality control to record production activities seamlessly. Meanwhile, the web-based backend aids warehouse operators in tracking raw materials and assists administrators with payroll and report generation. This research underscores how the Information System has effectively optimized production activities for quality control, warehouse operations, and administration at CV. Aya Sofya.

Optimizing Human-Robot Teaming Performance through Q-Learning-Based Task Load Adjustment and Physiological Data Analysis.

The transition to Industry 4.0 and 5.0 underscores the need for integrating humans into manufacturing processes, shifting the focus towards customization and personalization rather than traditional mass production. However, human performance during task execution may vary. To ensure high human-robot teaming (HRT) performance, it is crucial to predict performance without negatively affecting task execution. Therefore, to predict performance indirectly, significant factors affecting human performance, such as engagement and task load (i.e., amount of cognitive, physical, and/or sensory resources required to perform a particular task), must be considered. Hence, we propose a framework to predict and maximize the HRT performance. For the prediction of task performance during the development phase, our methodology employs features extracted from physiological data as inputs. The labels for these predictions-categorized as accurate performance or inaccurate performance due to high/low task load-are meticulously crafted using a combination of the NASA TLX questionnaire, records of human performance in quality control tasks, and the application of Q-Learning to derive task-specific weights for the task load indices. This structured approach enables the deployment of our model to exclusively rely on physiological data for predicting performance, thereby achieving an accuracy rate of 95.45% in forecasting HRT performance. To maintain optimized HRT performance, this study further introduces a method of dynamically adjusting the robot's speed in the case of low performance. This strategic adjustment is designed to effectively balance the task load, thereby enhancing the efficiency of human-robot collaboration.

ОЦІНКА НАПРУЖЕНОГО СТАНУ РОБОЧОГО ШАРУ ВАЛКІВ КОЕРЦИТИМЕТРИЧНИМ ЕКСПРЕС-МЕТОДОМ

The purpose of the work is the problem of researching the influence of chemical composition and structure on the indicators of operational stability of centrifugal two-layer rolling rolls made of high chromium cast iron by the coercimetric express method. In order to ensure the achievement of this goal, the following tasks were set and solved: conducting an analysis of the causes of the destruction of the surface layer of rolls; building a mathematical model for studying the influence of the chemical composition and structure of cast iron on the level of hardness and coercive force; using the coercimetric method to analyze the quality of rolled rolls. Conclusions. Forecasting the behavior of the rolls during operation is inextricably linked to the analysis of the main factors on which the level of properties and operational stability of the working layer depend. The properties of high-chromium alloys are closely related to the type of phases formed and their ratio. The amount of residual austenite and martensite in the structure of the alloy has the greatest influence on the properties of the alloy (in the studied interval of changes in the proportion of phases). The operational layer of two-layer high-chromium rolls is characterized by a high level of residual stresses. Exceeding the permissible level of stresses or their unfavorable distribution can cause premature destruction during the operation of the roll. With the help of the coercimetric express method, it is possible to solve a fairly wide range of tasks of quality control of rolls, related to the determination of the level and distribution of residual stresses in the working layer of the rolls. This is because the intensity of the process of formation of thermal cracks under conditions of thermo-cyclic loading largely depends on the level of residual compressive stresses. Too high a level of stresses or their unfavorable distribution can cause premature destruction of the working layer of the roll, because the typical type of destruction due to an unbalanced distribution of stresses is cracking. A local increase in the level of coercive force can be the basis of the prediction of crack formation.

Automatic Depth Shifting by Identifying and Matching Events on Well Logs Chicheng Xu

Depth matching or depth shifting between well logs acquired from different runs or between core scans and well logs is a critical data quality control task to ensure subsequent accurate petrophysical interpretation and modeling. Conventional depth-shifting workflow heavily relies on human expertise to manually match a series of peaks and troughs between log curves, which is often subjective, error-prone, and cumbersome. Therefore, it is necessary to establish an automatic depth-shifting workflow to perform this routine yet important task accurately in a consistent and efficient manner. We implemented an automatic workflow to emulate human expertise to identify important “events” such as peaks, troughs, and bed boundaries on log curves and then intelligently match the identified series of events between log curves with local maximum correlation criteria to generate a depth shift table. We applied the automatic workflow in a field case to shift the well log and core gamma ray and delivered a depth shift table comparable to manual depth matching. The final shifted log achieved a significantly enhanced correlation with the reference log. The events identifying and matching method presents a white-box solution that still follows the conventional petrophysical wisdom and allows more user interaction to fine-tune the results. The users have full control of the parameters for optimal results.

ResNet101-SVM: Hybrid convolutional neural network for citrus fruits classification

Recognizing and classifying citrus fruits is a challenging yet crucial task for agriculture, food processing, and quality control. Classifying citrus fruits is challenging because of their wide variety, often with a similar flesh appearance, shape, and size. Therefore, efficient and effective approaches are required for accurate identification. Our study focused on efficiently identifying citrus fruit types by utilizing a hybrid ResNet101-SVM model. ResNet101-SVM is the combination of the feature extraction capabilities of the ResNet101 with the classification power of SVM. This hybrid approach leverages the strengths of both deep learning (feature extraction) and traditional machine learning (SVM classification) to improve the accuracy and robustness of citrus fruit classification. The model outperformed the standard ResNet101 model across various performance metrics, achieving impressive accuracy, sensitivity, specificity, precision, F1 Score, MCC, and Kappa values of 99.81%, 99.81%, 99.8%, 99.82%, 0.18%, 99.81%, 99.80%, and 98.77%, respectively. This study holds significant promise for various applications, particularly in the domains of food processing and quality control.

Practice With Less AI Makes Perfect: Partially Automated AI During Training Leads to Better Worker Motivation, Engagement, and Skill Acquisition

The increased prevalence of human-AI collaboration is reshaping the manufacturing sector, fundamentally changing the nature of human work and training needs. While high automation improves performance when functioning correctly, it can lead to problematic human performance (e.g., defect detection accuracy, response time) when operators are required to intervene and assume manual control of decision-making responsibilities. As AI capability reaches higher levels of automation and human–AI collaboration becomes ubiquitous, addressing these performance issues is crucial. Proper worker training, focusing on skill-based, cognitive, and affective outcomes, and nurturing motivation and engagement, can be a mitigation strategy. However, most training research in manufacturing has prioritized the effectiveness of a technology for training, rather than how training design influences motivation and engagement, key to training success and longevity. The current study explored how training workers using an AI system affected their motivation, engagement, and skill acquisition. Specifically, we manipulated the level of automation of decision selection of an AI used for the training of 102 participants for a quality control task. Findings indicated that fully automated decision selection negatively impacted perceived autonomy, self-determined motivation, behavioral task engagement, and skill acquisition during training. Conversely, partially automated AI-enhanced motivation and engagement, enabling participants to better adapt to AI failure by developing necessary skills. The results suggest that involving workers in decision-making during training, using AI as a decision aid rather than a decision selector, yields more positive outcomes. This approach ensures that the human aspect of manufacturing work is not overlooked, maintaining a balance between technological advancement and human skill development, motivation, and engagement. These findings can be applied to enhance real-world manufacturing practices by designing training programs that better develop operators’ technical, methodological, and personal skills, though companies may face challenges in allocating substantial resources for training redevelopment and continuously adapting these programs to keep pace with evolving technology.

Mitigating Bias in Aesthetic Quality Control Tasks: An Adversarial Learning Approach

Aesthetic quality control (AQC) is an essential step in smart factories to ensure that product quality meets the desired standards. This operation includes assessing factors such as color, texture, and shape. In the context of AQC, bias can arise when the criteria used to evaluate the aesthetics of a product are subjective and influenced by personal preferences. Bias can also occur due to the background or other objective factors like the geometry of the material. This work will focus on applying an adversarial learning strategy to a pre-trained DL architecture for improving the generalization performance of a predictive model tailored explicitly for solving AQC task classification. Experimental results on a benchmark AQC dataset highlighted the robustness of the proposed methodology for learning only relevant components related to quality classes rather than other confusing traits, enabling the mitigation of the identified bias.

DES-YOLO: a novel model for real-time detection of casting surface defects.

Surface defect inspection methods have proven effective in addressing casting quality control tasks. However, traditional inspection methods often struggle to achieve high-precision detection of surface defects in castings with similar characteristics and minor scales. The study introduces DES-YOLO, a novel real-time method for detecting castings' surface defects. In the DES-YOLO model, we incorporate the DSC-Darknet backbone network and global attention mechanism (GAM) module to enhance the identification of defect target features. These additions are essential for overcoming the challenge posed by the high similarity among defect characteristics, such as shrinkage holes and slag holes, which can result in decreased detection accuracy. An enhanced pyramid pooling module is also introduced to improve feature representation for small defective parts through multi-layer pooling. We integrate Slim-Neck and SIoU bounding box regression loss functions for real-time detection in actual production scenarios. These functions reduce memory overhead and enable real-time detection of surface defects in castings. Experimental findings demonstrate that the DES-YOLO model achieves a mean average precision (mAP) of 92.6% on the CSD-DET dataset and a single-image inference speed of 3.9 milliseconds. The proposed method proves capable of swiftly and accurately accomplishing real-time detection of surface defects in castings.

From leaves to labels: Building modular machine learning networks for rapid herbarium specimen analysis with LeafMachine2.

Quantitative plant traits play a crucial role in biological research. However, traditional methods for measuring plant morphology are time consuming and have limited scalability. We present LeafMachine2, a suite of modular machine learning and computer vision tools that can automatically extract a base set of leaf traits from digital plant data sets. LeafMachine2 was trained on 494,766 manually prepared annotations from 5648 herbarium images obtained from 288 institutions and representing 2663 species; it employs a set of plant component detection and segmentation algorithms to isolate individual leaves, petioles, fruits, flowers, wood samples, buds, and roots. Our landmarking network automatically identifies and measures nine pseudo-landmarks that occur on most broadleaf taxa. Text labels and barcodes are automatically identified by an archival component detector and are prepared for optical character recognition methods or natural language processing algorithms. LeafMachine2 can extract trait data from at least 245 angiosperm families and calculate pixel-to-metric conversion factors for 26 commonly used ruler types. LeafMachine2 is a highly efficient tool for generating large quantities of plant trait data, even from occluded or overlapping leaves, field images, and non-archival data sets. Our project, along with similar initiatives, has made significant progress in removing the bottleneck in plant trait data acquisition from herbarium specimens and shifted the focus toward the crucial task of data revision and quality control.

Development of image-based fast defect recognition and localization network (FDRLNet) for steel surfaces

The utilization of vision-based systems for automated inspection and quality control tasks increased in recent years due to the adaptation of Industry 4.0 initiatives in manufacturing. Continuous steel production units extensively employ vision-based solutions to classify and localize surface defects. The inspection system must provide quick and reliable feedback about surface defect type (classification) and location (localization) utilizing images acquired from the camera. This paper presents a novel surface defect detector, Fast Defect Recognition and Localization Network (FDRLNet), for achieving accurate prediction abilities at higher inference speeds. The robustness of the proposed approach is validated by utilizing publicly available Northeastern University (NEU-DET) surface defect dataset. The prediction abilities are corroborated by comparing the mean Average Precision (mAP) and inference speed with other competitive approaches presented in the literature. It has been shown that the proposed approach has robust prediction abilities at higher inference speeds and can be implemented in real-time defect detection tasks.

LSD-YOLOv5: A Steel Strip Surface Defect Detection Algorithm Based on Lightweight Network and Enhanced Feature Fusion Mode.

In the field of metallurgy, the timely and accurate detection of surface defects on metallic materials is a crucial quality control task. However, current defect detection approaches face challenges with large model parameters and low detection rates. To address these issues, this paper proposes a lightweight recognition model for surface damage on steel strips, named LSD-YOLOv5. First, we design a shallow feature enhancement module to replace the first Conv structure in the backbone network. Second, the Coordinate Attention mechanism is introduced into the MobileNetV2 bottleneck structure to maintain the lightweight nature of the model. Then, we propose a smaller bidirectional feature pyramid network (BiFPN-S) and combine it with Concat operation for efficient bidirectional cross-scale connectivity and weighted feature fusion. Finally, the Soft-DIoU-NMS algorithm is employed to enhance the recognition efficiency in scenarios where targets overlap. Compared with the original YOLOv5s, the LSD-YOLOv5 model achieves a reduction of 61.5% in model parameters and a 28.7% improvement in detection speed, while improving recognition accuracy by 2.4%. This demonstrates that the model achieves an optimal balance between detection accuracy and speed, while maintaining a lightweight structure.

Pervasive Augmented Reality to support logistics operators in industrial scenarios: a shop floor user study on kit assembly

Augmented Reality (AR) is a pillar of the transition to Industry 4.0 and smart manufacturing. It can facilitate training, maintenance, assembly, quality control, remote collaboration and other tasks. AR has the potential to revolutionize the way information is accessed, used and exchanged, extending user’s perception and improving their performance. This work proposes a Pervasive AR tool, created with partners from the industry sector, to support the training of logistics operators on industrial shop floors. A Human-Centered Design (HCD) methodology was used to identify operators difficulties, challenges, and define requirements. After initial meetings with stakeholders, two distinct methods were considered to configure and visualize AR content on the shop floor: Head-Mounted Display (HMD) and Handheld Device (HHD). A first (preliminary) user study with 26 participants was conducted to collect qualitative data regarding the use of AR in logistics, from individuals with different levels of expertise. The feedback obtained was used to improve the proposed AR application. A second user study was realized, in which 10 participants used different conditions to fulfill distinct logistics tasks: C1 — paper; C2 — HMD; C3 — HHD. Results emphasize the potential of Pervasive AR in the operators’ workspace, in particular for training of operators not familiar with the tasks. Condition C2 was preferred by all participants and considered more useful and efficient in supporting the operators activities on the shop floor.

An Unsupervised Machine-Learning Workflow for Outlier Detection and Log Editing With Prediction Uncertainty

Recent advances in data science and machine learning (ML) have brought the benefits of these technologies closer to the mainstream of petrophysics. ML systems, where decisions and self-checks are made by carefully designed algorithms, in addition to executing typical tasks such as classification and regression, offer efficient and liberating solutions to the modern petrophysicist. The outline of such a system and its application in the form of a multilevel workflow to a 59-well multifield study are presented in this paper. The main objective of the workflow is to identify outliers in bulk density and compressional slowness logs and to reconstruct them using data-driven predictive models. A secondary objective of the project is to predict shear slowness in zones where such data do not exist. The system is fully automated, designed to optimize the use of all available data, and provide uncertainty estimates. It integrates modern concepts for outlier detection, predictive classification, and regression, as well as multidimensional scaling based on inter-well similarity. Benchmarking of ML results against those created by experienced petrophysicists shows that the ML workflow can provide high-quality answers that compare favorably to those produced by human experts. A second validation exercise, that compares acoustic impedance logs computed from ML answers to actual seismic data, provides further evidence for the accuracy of the ML-generated results. The ML system supports the petrophysicist by easing the burden on repetitive and burdensome quality control tasks. The efficiency gains and time savings created can be used for enhanced effective cross-discipline integration, collaboration, and further innovation.

Color Classification Under Complex Background via Genetic Algorithm-Based Color Difference Histogram

Color classification of polycrystalline silicon solar cells is really challenging for performing the task of production quality control during the manufacturing due to the non-Gaussian color distribution and random texture background. The motivation of this work is to present a robust color classification technique by designing a novel tiny color difference feature descriptor. Thus, a genetic algorithm based color difference histograms (GACDH) is proposed. First, the optimal color space of color difference histogram (CDH) to represent tiny color changes is designed. It counts the perceptually uniform color difference in a small local neighborhood in the L*a*b* color space, which reduces the false classification due to small color variations and illumination variation. Second, the genetic algorithm based color quantization for CDH is proposed to select the optimal quantization bins in the L* component, then we make some comparative experiments in a* and b* color components to select optimal quantization bins. The optimization of feature dimension not only reduces the large dimensionality of histogram bins in the computation but also improves the following classification performance. Finally, the proposed algorithm is validated with color dataset of solar cells with distance measure method. Some experimental results and analysis show that the overall performance of the proposed method achieves 98.6% and outperforms other techniques available in the literature in terms of weak discriminative color difference classification.