Maturity Classification Research Articles

Maturity Classification of Rapeseed Using Hyperspectral Image Combined with Machine Learning.

Oilseed rape is an important oilseed crop planted worldwide. Maturity classification plays a crucial role in enhancing yield and expediting breeding research. Conventional methods of maturity classification are laborious and destructive in nature. In this study, a nondestructive classification model was established on the basis of hyperspectral imaging combined with machine learning algorithms. Initially, hyperspectral images were captured for 3 distinct ripeness stages of rapeseed, and raw spectral data were extracted from the hyperspectral images. The raw spectral data underwent preprocessing using 5 pretreatment methods, namely, Savitzky-Golay, first derivative, second derivative (D2nd), standard normal variate, and detrend, as well as various combinations of these methods. Subsequently, the feature wavelengths were extracted from the processed spectra using competitive adaptive reweighted sampling, successive projection algorithm (SPA), iterative spatial shrinkage of interval variables (IVISSA), and their combination algorithms, respectively. The classification models were constructed using the following algorithms: extreme learning machine, k-nearest neighbor, random forest, partial least-squares discriminant analysis, and support vector machine (SVM) algorithms, applied separately to the full wavelength and the feature wavelengths. A comparative analysis was conducted to evaluate the performance of diverse preprocessing methods, feature wavelength selection algorithms, and classification models, and the results showed that the model based on preprocessing-feature wavelength selection-machine learning could effectively predict the maturity of rapeseed. The D2nd-IVISSA-SPA-SVM model exhibited the highest modeling performance, attaining an accuracy rate of 97.86%. The findings suggest that rapeseed maturity can be rapidly and nondestructively ascertained through hyperspectral imaging.

The Image Extraction Using the HSV Method to Determine the Maturity Level of Palm Oil Fruit with the k-nearest Neighbor Algorithm

The oil palm is one of the monocot oil-producing plants in Indonesia. Sorting errors in oil palm fruit are caused by a sorter error when distinguishing the color of ripe and immature oil palm fruit. In addition to inefficient time, the area of oil palm plantations is also a factor that causes the sorter to make mistakes in sorting. This study aims to produce a system that can classify the maturity of oil palms based on feature extraction of characteristics of the hue, saturation and value (HSV) color features. The HSV method is used to produce color characteristics from the image of the oil palm fruit. Classification of oil palm fruit maturity is classified using the K-Nearest Neighbor (KNN) algorithm with a dataset of 400 oil palm fruit image data with a data sharing ratio of 70% training data and 30% test data. 280 image data were used as training data, divided into 140 image data of ripe oil palm fruit, 140 image data of immature oil palm fruit and 120 image data of oil palm used as test data which is divided into 60 image data of ripe oil palm and 45 unripe palm oil. Based on the result of tests that have been carried out using a confusion matrix with varied k values, namely, 5 and 7, the average precision is 94.16%.

Comprehensive Analysis of Model Errors in Blueberry Detection and Maturity Classification: Identifying Limitations and Proposing Future Improvements in Agricultural Monitoring

In blueberry farming, accurately assessing maturity is critical to efficient harvesting. Deep Learning solutions, which are increasingly popular in this area, often undergo evaluation through metrics like mean average precision (mAP). However, these metrics may only partially capture the actual performance of the models, especially in settings with limited resources like those in agricultural drones or robots. To address this, our study evaluates Deep Learning models, such as YOLOv7, RT-DETR, and Mask-RCNN, for detecting and classifying blueberries. We perform these evaluations on both powerful computers and embedded systems. Using Type-Influence Detector Error (TIDE) analysis, we closely examine the accuracy of these models. Our research reveals that partial occlusions commonly cause errors, and optimizing these models for embedded devices can increase their speed without losing precision. This work improves the understanding of object detection models for blueberry detection and maturity estimation.

Tomato maturity recognition with convolutional transformers

Tomatoes are a major crop worldwide, and accurately classifying their maturity is important for many agricultural applications, such as harvesting, grading, and quality control. In this paper, the authors propose a novel method for tomato maturity classification using a convolutional transformer. The convolutional transformer is a hybrid architecture that combines the strengths of convolutional neural networks (CNNs) and transformers. Additionally, this study introduces a new tomato dataset named KUTomaData, explicitly designed to train deep-learning models for tomato segmentation and classification. KUTomaData is a compilation of images sourced from a greenhouse in the UAE, with approximately 700 images available for training and testing. The dataset is prepared under various lighting conditions and viewing perspectives and employs different mobile camera sensors, distinguishing it from existing datasets. The contributions of this paper are threefold: firstly, the authors propose a novel method for tomato maturity classification using a modular convolutional transformer. Secondly, the authors introduce a new tomato image dataset that contains images of tomatoes at different maturity levels. Lastly, the authors show that the convolutional transformer outperforms state-of-the-art methods for tomato maturity classification. The effectiveness of the proposed framework in handling cluttered and occluded tomato instances was evaluated using two additional public datasets, Laboro Tomato and Rob2Pheno Annotated Tomato, as benchmarks. The evaluation results across these three datasets demonstrate the exceptional performance of our proposed framework, surpassing the state-of-the-art by 58.14%, 65.42%, and 66.39% in terms of mean average precision scores for KUTomaData, Laboro Tomato, and Rob2Pheno Annotated Tomato, respectively. This work can potentially improve the efficiency and accuracy of tomato harvesting, grading, and quality control processes.

Convolutional neural network-assisted diagnosis of midpalatal suture maturation stage in cone-beam computed tomography

ObjectivesThe selection of treatment for maxillary expansion is closely related to the calcification degree of the midpalatal suture. A classification method for individual assessment of the morphology of midpalatal suture in cone-beam computed tomography (CBCT) is useful for evaluating the calcification degree. Currently, convolutional neural networks (CNNs) have been introduced into the field of oral and maxillofacial imaging diagnosis. This study validated the ability of CNN models in assessing the maturation stage of the midpalatal suture. MethodsThe existing CNN model ResNet50 was trained to locate the CBCT transverse plane which contained a complete midpalatal suture. ResNet18, ResNet50, RessNet101, Inception-v3, and Efficientnetv2-s models were trained to evaluate the midpalatal suture maturation stage. Multi-class classification metrics, accuracy, recall, precision, F1-score, and area under the curve values from the receiver operating characteristic curve were used to evaluate the performance of the models, and gradient-weighted class activation map technology was utilised to visualise five midpalatal suture maturation stages for each model. ResultsResnet50 demonstrated an accuracy of 99.74 % in identifying the transverse plane that contained the complete midpalatal suture. The highest accuracies achieved on the two-stage, three-stage, and five-stage maturation classification tests were 95.15, 88.06, and 75.37 %, all of which exceeded the average accuracy of three experienced orthodontists. ConclusionsThe CNN model can locate the plane of the midpalatal suture in CBCT images and can assist clinicians in assessing the maturation stage of the midpalatal suture to select the means of maxillary expansion. Clinical significanceThe application of artificial intelligence on CBCT midpalatal suture plane localisation and maturation stage evaluation enhances diagnostic and treatment efficiency and accuracy of individual assessment of midpalatal suture calcification degree. Additionally, it assists the clinical palatal expansion technique in achieving ideal results.

Tobacco Leaves Maturity Classification Based on Deep Learning and Proximal Hyperspectral Imaging

Accurately measuring tobacco harvest maturity is crucial for optimizing quality and crop management. Traditional methods heavily rely on qualitative evaluation and chemical experiments, which introduce subjectivity and inherent limitations. This study proposes a novel method that combines deep learning with proximal hyperspectral imaging (HSI) to achieve precise recognition of tobacco leaf maturity. Unlike traditional techniques, HSI captures rich spectral and spatial data, enabling comprehensive analysis. It adopts a pixel-level annotation strategy to annotate each pixel based on its maturity level, thereby preserving spectral complexity. The dataset comprises 3000 randomly extracted cubes ( 5 × 5 × 176 ) from 150 original hyperspectral images, encompassing five maturity levels. Spectral and spatial features are extracted from hyperspectral data using a three-dimensional convolutional neural network (3D-CNN) architecture. This method effectively leverages complex spectral patterns for maturity recognition. During testing, the model demonstrated an impressive average accuracy of 99.93%. Visual predictions vividly illustrate the model’s proficiency in maturity recognition, affirming its practical utility. This study pioneers the integration of deep learning and hyperspectral near-end sensing technology in tobacco maturity assessment, mitigating the constraints of traditional methods, and establishing the groundwork for real-time monitoring and quality control of tobacco.

Agave crop segmentation and maturity classification with deep learning data-centric strategies using very high-resolution satellite imagery

ABSTRACTThe responsible and sustainable agave-tequila production chain is fundamental for the social, environmental, and economic development of Mexico’s agave regions. It is therefore relevant to develop new tools for large-scale automatic agave region monitoring. In this work, we present an Agave tequilana Weber azul crop segmentation and maturity classification using very high-resolution satellite imagery, which could be useful for this task. To achieve this, we solve real-world deep learning problems in the very specific context of agave crop segmentation such as a lack of data, low-quality labels, highly imbalanced data, and low model performance. The proposed strategies go beyond data augmentation and data transfer combining active learning and the creation of synthetic images with human supervision. As a result, the segmentation performance evaluated with the Intersection over Union (IoU) value increased from 0.72 to 0.90 in the test set. The authors also propose a method for classifying agave crop maturity with 95% accuracy. With the resulting accurate models, agave production forecasting can be available for large regions. In addition, some supply-demand problems such as excessive supplies of agave or, deforestation, could be detected early.

Klasifikasi Tingkat Kematangan Buah Sawit Berbasis Deep Learning dengan Menggunakan Arsitektur Yolov5

Object identification and recognition in the field of computer vision is undergoing rapid development and is applied to various fields, ranging from industry to the health sector. This is reflected in the amount of research conducted, including a focus on the application and personalization of machine learning, as well as the development of new models to solve specific problems and challenges. In the palm oil industry, fruit maturity is divided into two categories, namely immature and ripe. Traditionally, fruit maturity is determined visually by experienced workers based on the number of fruits falling from the bunch or the color of the bunch. However, this technique has disadvantages such as the reduced amount of oil when many fruits fall from the bunch and the subjective assessment of fruit color. Therefore, the purpose of this research is to create an oil palm fruit maturity classification system based on YOLO v5. The dataset used consists of 1500 photos and the annotation data is created with roboflow. The final result is divided into three categories, namely ripe, immature, and rotten. The YOLOv5s algorithm was used to train the dataset. Based on the model estimation results, mAP reached 92%, accuracy reached 97%, and recall reached 96%. The last step is real-time system testing.

Research on the Strawberry Recognition Algorithm Based on Deep Learning

In view of the time-consuming and laborious manual picking and sorting of strawberries, the direct impact of image recognition accuracy on automatic picking and the rapid development of deep learning(DL), a Faster Regions with Convolutional Neural Network features (R-CNN) strawberry recognition method that combines Mixup data augmentation, a ResNet(Residual Network)50 backbone feature extraction network and a Soft-NMS (Non-Maximum Suppression) algorithm, named the MRS Faster R-CNN, is proposed. In this paper, the transfer learning backbone feature extraction network VGG (Visual Geometry Group) 16 and ResNet50 are compared, and the superior ResNet50 is selected as the backbone network of MRS Faster R-CNN. The data augmentation method of Mixup image fusion is used to improve the learning and generalization ability of the model. The redundant bboxes (bounding boxes) are removed through Soft-NMS to obtain the best region proposal. The freezing phase is added to the training process, effectively reducing the occupation of video memory and shortening the training time. After experimental verification, the optimized model improved the AP (Average Precision) values of mature and immature strawberries by 0.26% and 5.34%, respectively, and the P(Precision) values by 0.81% and 6.34%, respectively, compared to the original model (R Faster R-CNN). Therefore, the MRS Faster R-CNN model proposed in this paper has great potential in the field of strawberry recognition and maturity classification and improves the recognition rate of small fruit and overlapping occluded fruit, thus providing an excellent solution for mechanized picking and sorting.

Ambon Banana Maturity Classification Based On Convolutional Neural Network (CNN)

The banana (Musa paradical), is an excellent fruit produced nationally and high in vitamins. In Indonesia, banana production is at a higher level than other fruit products. However, one of them is the issue with bananas' post-harvest, which arises when they are produced in huge quantities on a large scale or by an industry that sorts bananas. So far, the determination of the maturity level of bananas is done by relying on visual analysis limited to the color of the skin by the human eye. However, this identification approach has several drawbacks. First, this method requires significant effort in the banana sorting process. In addition, the perception of the fruit's maturity level can vary, because humans can experience fatigue and lack of consistency in judgment. In addition, human judgment is also influenced by subjective factors that can affect the final result. Considering this problem, developed a system to classify the ripeness level of Ambon bananas. This system utilizes image enhancement features to increase contrast, which is implemented using a Convolutional Neural Network (CNN). The classification process is carried out through image processing using MATLAB R2022a software, which forms the basis of a classification system with 4 classes which include 486 images of unripe Ambon bananas, 235 images of half-ripe Ambon bananas, 309 images of perfectly ripe Ambon bananas, 184 images of rotten Ambon bananas. The dataset analyzed in this study totaled 1214 data divided into 1093 training data and 121 test data. The CNN method is used in this data classification, and the results show an accuracy rate of 95.87%.

Effect of dietary inclusion of microalgae (Nannochloropsis gaditana and Schizochytrium spp) on non-specific immunity and erythrocyte maturity in Atlantic salmon fingerlings.

The parr-smolt transformation in salmonids involves a critical period characterized by systemic changes associated with the fish's immune response. In this context, as a dietary ingredient in functional diets, microalgae offer an alternative due to their nutritional and bioactive compounds that could strengthen the immune status. This study evaluated the effect of a diet supplemented with Schizochytrium spp and Nannochloropsis gaditana on the expression of genes associated with the antibacterial response. Additionally, the study assessed the effect on the leukocyte population and erythrocyte maturity in Salmo salar blood. Fish were fed for 30 days with a microalgal mixture (1:1) at a 10% inclusion. Each diet was randomly assigned to a tank using a completely randomized design (CRD) with four replications. Each tank was stocked with 70 Atlantic salmon fingerlings with an initial mean weight of 78.87±0.84. Transcription levels were quantified and analyzed by qRT-PCR from cell isolates and mucus tissue. Furthermore, cell count and identification of leukocytes and classification of cellular maturity of erythrocytes using a neural network with a multilayer perceptron (MLP) were performed. Our results showed a significant (p<0.05) increase in fold change expression of C3 (2.54±0.65) and NK-Lysine (6.84±0.94) in erythrocytes of microalgae-supplemented fish. Moreover, a significant increase of 1.59 and 2.35 times in monocytes and immature erythrocytes, respectively, was observed in the same group of fish (p<0.05). This study's results indicate that dual microalgae (Schizochytrium spp and N. gaditana) supplementation can increase innate humoral antibacterial components, particularly in erythrocyte tissue, and increase phagocytic cells and immature erythrocytes in S. salar blood.

Potential of multispectral imaging for maturity classification and recognition of oriental melon

Potential of multispectral imaging for maturity classification and recognition of oriental melon

Radiographic assessment of the pubic symphysis in elite male adolescent football players: Development and reliability of the Maturing Adolescent Pubic Symphysis (MAPS) classification

IntroductionThe pubic symphysis is susceptible to growth related injuries long after the adolescent growth spurt. Our study describes the radiographic maturation of the pubic symphysis on pelvic radiographs in adolescent football players and introduces the Maturing Adolescent Pubic Symphysis classification (MAPS classification). MethodsAnteroposterior pelvic radiographs of 105 healthy adolescent male football players between 12 and 24 years old were used to develop the classification system. The radiological scoring of the symphyseal joint was developed over five rounds. The final MAPS classification items were scored in random order by two experienced readers, blinded to the age of the participant and to each other’s scoring. The inter- and intra-rater reliability were examined using weighted kappa (κ). ResultsWe developed a classification system with descriptive definitions and an accompanying pictorial atlas. The symphyseal joint was divided into three regions: the superior corners, and the upper and lower regions of the joint line. Inter-rater reliability was substantial to almost perfect: superior region: κ = 0.70 (95% CI 0.60–––0.79), upper region of the joint line: κ = 0.89 (95% CI 0.86–––0.92), lower region of the joint line: κ = 0.65 (95% CI 0.55–––0.75). The intra-observer reliability showed similar results. ConclusionThe Maturing Adolescent Pubic Symphysis classification (MAPS classification) is a reliable descriptive classification of the radiographic maturation of the pubic symphysis joint in athletic males. The stages can provide a basis for understanding in clinical practice and will allow future research in this field.

A Real-Time Detection and Maturity Classification Method for Loofah

Fruit maturity is a crucial index for determining the optimal harvesting period of open-field loofah. Given the plant’s continuous flowering and fruiting patterns, fruits often reach maturity at different times, making precise maturity detection essential for high-quality and high-yield loofah production. Despite its importance, little research has been conducted in China on open-field young fruits and vegetables and a dearth of standards and techniques for accurate and non-destructive monitoring of loofah fruit maturity exists. This study introduces a real-time detection and maturity classification method for loofah, comprising two components: LuffaInst, a one-stage instance segmentation model, and a machine learning-based maturity classification model. LuffaInst employs a lightweight EdgeNeXt as the backbone and an enhanced pyramid attention-based feature pyramid network (PAFPN). To cater to the unique characteristics of elongated loofah fruits and the challenge of small target detection, we incorporated a novel attention module, the efficient strip attention module (ESA), which utilizes long and narrow convolutional kernels for strip pooling, a strategy more suitable for loofah fruit detection than traditional spatial pooling. Experimental results on the loofah dataset reveal that these improvements equip our LuffaInst with lower parameter weights and higher accuracy than other prevalent instance segmentation models. The mean average precision (mAP) on the loofah image dataset improved by at least 3.2% and the FPS increased by at least 10.13 f/s compared with Mask R-CNN, Mask Scoring R-CNN, YOLACT++, and SOLOv2, thereby satisfying the real-time detection requirement. Additionally, a random forest model, relying on color and texture features, was developed for three maturity classifications of loofah fruit instances (M1: fruit setting stage, M2: fruit enlargement stage, M3: fruit maturation stage). The application of a pruning strategy helped attain the random forest model with the highest accuracy (91.47% for M1, 90.13% for M2, and 92.96% for M3), culminating in an overall accuracy of 91.12%. This study offers promising results for loofah fruit maturity detection, providing technical support for the automated intelligent harvesting of loofah.

Nondestructive quality assessment and maturity classification of loquats based on hyperspectral imaging

The traditional method for assessing the quality and maturity of loquats has disadvantages such as destructive sampling and being time-consuming. In this study, hyperspectral imaging technology was used to nondestructively predict and visualise the colour, firmness, and soluble solids content (SSC) of loquats and discriminate maturity. On comparison of the performance of different feature variables selection methods and the calibration models, the results indicated that the multiple linear regression (MLR) models combined with the competitive adaptive reweighting algorithm (CARS) yielded the best prediction performance for loquat quality. Particularly, CARS-MLR models with optimal prediction performance were obtained for the colour (R2P = 0.96, RMSEP = 0.45, RPD = 5.38), firmness (R2P = 0.87, RMSEP = 0.23, RPD = 2.81), and SSC (R2P = 0.84, RMSEP = 0.51, RPD = 2.54). Subsequently, distribution maps of the colour, firmness, and SSC of loquats were obtained based on the optimal CARS-MLR models combined with pseudo-colour technology. Finally, on comparison of different classification models for loquat maturity, the partial least square discrimination analysis model demonstrated the best performance, with classification accuracies of 98.19% and 97.99% for calibration and prediction sets, respectively. This study demonstrated that the hyperspectral imaging technique is promising for loquat quality assessment and maturity classification.

Introduction to Citrus Fruit Ripens Using the Deep Learning Convolutional Neural Network (CNN) Learning Method

The export value of Indonesian fruits in 2023 will increase compared to 2021. For this reason, a program is needed to introduce fruit maturity, in this case, citrus fruits. Currently, the fruit maturity recognition system is still done manually which takes a long time and requires a lot of human resources. Thus, the purpose of this research is to use Machine Learning and the Convolution Neural Network (CNN) model in the classification of citrus fruit maturity. The computer image recognition method used is CNN, which has advantages in computer vision applications, face recognition, object detection, image recognition, and visual recognition. Datasets in the form of orange images are collected to be applied to the Machine Learning method. The test results showed that training accuracy reached 100% and validation accuracy reached 86.59% after 40 epochs using the CNN method on local varieties of orange images. Training loss reaches 0.7 and validation loss reaches 0.69 after 40 epochs.

Image Classification of Tempe Fermentation Maturity Using Naïve Bayes Based on Linear Discriminant Analysis

One of the foods in Indonesia that has a lot of nutritional content and benefits, one of which is tempeh. Tempe is usually made by fermenting soybeans with mold under special conditions to become tempeh. In the fermentation process, tempeh producers need to monitor the maturity of the tempeh until it is suitable for consumption. To detect this maturity requires a separate effort, so that an image processing approach is proposed in this study with the support of feature selection. An image allows for various features to be taken, such as texture features using GLCM and various color features including RGB, HSV, LAB, CMYK, YUV, HCL, HIS, LCH. With so many features, it is necessary to do a selection so that computation in its classification becomes efficient. This study aims to classify tempeh fermented images using the Naive Bayes method with Linear Discriminant Analysis (LDA)feature selection for GLCM features and eight color features. Tempe fermentation image is divided into three classes, namely raw, ripe and rotten. Based on the experimental results, the average accuracy in the test is 84.06%. In testing the fastest time is 1.87 seconds and the longest is 2.20 seconds. This shows that the classification of fermented tempeh maturity with Naive Bayes with LDA feature selection can work well.

Effect of maturity stages on the quality indices of wood apple (Feronia limonia) and modeling of its kinetics by applying machine learning approaches

In the present investigation, an inexpensive and non-destructive method was tested for the appropriate maturity classification of wood apple (Feronia limonia). The investigation was conducted to establish the pronounced effect of maturity stages on the growth kinetics, physico-chemical properties, and other quality indices of wood apple. A systematic trend was observed for all the properties namely sphericity, bulk density (g/cm3), true density (g/cm3), pH, total soluble solids TSS (°Brix), titratable acidity (%) and TSS/TA ratio, etc. of the fruit. In contrast, regular changes were also observed in the color properties at various maturity stages of the wood apple. The maturity kinetics was formulated by applying recurrent neural network (RNN) in compliance with K means cluster algorithm. RNN modeling was applied by considering color property (redness value) as input and six maturity indices as the output of the formulated structure. The RNN architecture, 1-6-6 showed the best results for forecasting the wood apple maturity based on color features. Further, based on the results of the K means cluster algorithm, the maturity stages were classified into three main categories, illustrated in the form of a simplified color chart. Hence, this investigation can be useful for proper control and identification of wood apple maturity during the processing.

Enhanced Efficiency of Coffee Fruit Ripe Sorting System through Ultrasound-based Optimization and Fuzzy Logic

This research focuses on the development of a coffee fruit sorting system, which is a part of an embedded automation system for coffee processing and storage. The implementation of this system aims to improve and maintain the quality of coffee throughout the production and storage processes. The embedded automation system for coffee processing begins with the coffee fruit sorting system, which is responsible for selecting perfectly ripe and high-quality coffee fruits. Subsequently, the system proceeds with coffee bean production and storage processes. The developed system comprises small-scale subsystems capable of performing various coffee processing tasks. These subsystems can be integrated to form a larger system capable of handling coffee production and storage processes. The research utilizes software technology embedded in the hardware system. The employed software technology is a component of an intelligent control system, which utilizes artificial intelligence as its underlying control mechanism. The maturity classification of coffee fruits is divided into three classes: KM (immature), MM (mature), and MS (fully mature). This classification scheme simplifies the understanding of the sorting process.

Classification of Cocoa Pod Maturity Using Similarity Tools on an Image Database: Comparison of Feature Extractors and Color Spaces

Côte d’Ivoire, the world’s largest cocoa producer, faces the challenge of quality production. Immature or overripe pods cannot produce quality cocoa beans, resulting in losses and an unprofitable harvest. To help farmer cooperatives determine the maturity of cocoa pods in time, our study evaluates the use of automation tools based on similarity measures. Although standard techniques, such as visual inspection and weighing, are commonly used to identify the maturity of cocoa pods, the use of automation tools based on similarity measures can improve the efficiency and accuracy of this process. We set up a database of cocoa pod images and used two feature extractors: one based on convolutional neural networks (CNN), in particular, MobileNet, and the other based on texture analysis using a gray-level co-occurrence matrix (GLCM). We evaluated the impact of different color spaces and feature extraction methods on our database. We used mathematical similarity measurement tools, such as the Euclidean distance, correlation distance, and chi-square distance, to classify cocoa pod images. Our experiments showed that the chi-square distance measurement offered the best accuracy, with a score of 99.61%, when we used GLCM as a feature extractor and the Lab color space. Using automation tools based on similarity measures can improve the efficiency and accuracy of cocoa pod maturity determination. The results of our experiments prove that the chi-square distance is the most appropriate measure of similarity for this task.