English
हिन्दी
Evaluation and Segregation of Fruit Quality using Machine and Deep Learning Techniques
| 1. Abstract - | 2. Introduction - |
|
Identifying fruit fruits is an essential part of fruit plantation smart management. This paper presents a mechanism based on the available deep learning model to determine the fruit fast and reliably in a complicated orchard environment. We employed the YOLOv3 method to detect the deep characteristics of fruit fruits using a stereo camera and an indoor fruit dataset, resulting in efficient identification of varied fruit sizes.The YOLOv3 model has been used for fruit object detection with boundary regions. It returns the normalized image in square form with the detection of edges of the object the UNET framework has used for classification. The various backbones obtain different accuracy, but UNET-VGG19 brings Dice Coefficient of 90.35%, which is better than other methods |
With the paucity of agricultural work and the speedy development of artificial intelligence (AI), robots have received much interest in the agricultural area. Agricultural robots perform time-consuming farm tasks, allowing farmers to concentrate more on farm management. Amongst the most famous agricultural robots is the harvesting robot. Harvesting robots have grown greatly in speed and efficiency in recent times, and people are becoming more enthusiastic in using agricultural robots to extract fruits and veggies. Several investigations on fruit identification have been conducted recently. The best way to achieve automated harvesting is a vision technology, and correct detection is the foundation of follow-up operations including picking in fruit or vegetable harvesting. |
| 3. Previous work- | 4. Project Work - |
|
Evaluation and segregation of fruit quality using machine and deep learning techniques is a growing field of research that combines computer vision, machine learning, and deep learning techniques to analyze and classify fruit based on their quality attributes such as color, size, shape, and defects.The process typically involves capturing images of the fruit using cameras or other sensors and then using machine learning algorithms to analyze the images and identify the quality attributes of the fruit. The goal is to accurately classify the fruit into different categories based on their quality attributes, which can be used to sort and grade the fruit for various purposes, such as for sale in supermarkets or for use in food processing. |
The following is an outline of a project that can be undertaken for the evaluation and segregation of fruit quality using machine and deep learning techniques: Data Collection: Collect data on various parameters that affect the quality of fruits. These parameters could include color, size, shape, texture, and weight. Data Preprocessing: Clean the collected data by removing missing values, outliers, and inconsistencies. Normalize the data to ensure that each parameter has the same scale. Feature Extraction: Extract relevant features from the preprocessed data that can help in evaluating the quality of fruits. This could include using image processing techniques to extract color, size, and shape features from images of the fruits. Overall, the project aims to automate the evaluation and segregation of fruit quality using machine and deep learning techniques, thereby improving the accuracy and efficiency of this important task in the food industry. |
| 5. Result - | |
|
n our propose model with unet_vgg19 at input RGB state the dice coefficient is 90.35% and with this dice coefficient the recall is 88.23% and the final precision is 93.04% and in other state of unet_vgg19 at input HSV the dice coefficient is 89.90% and with this dice coefficient the recall is 87.26% and the final precision is 93.29% and our this calculation is better than other methods |
High accuracy: A well-trained machine or deep learning model can achieve high accuracy in evaluating and segregating fruits based on their quality. The accuracy can be measured using metrics such as precision, recall, and F1-score. For example, an SVM or CNN model can achieve an accuracy of over 90% in classifying fruits into high-quality and low-quality categories.Improved efficiency: Automating the evaluation and segregation of fruit quality using machine and deep learning techniques can improve the efficiency of the process. It can reduce the time and resources required for manual inspection and increase the speed of fruit grading and sorting |
| 6. Conclusion | |
|
|
The precise detection of fruits is critical for the intelligent administration of fruit detection and classification. In this paper, we propose a identification approach for fruit detection in the natural surroundings depending on the proposed YOLOv3 model for preprocessing and UNET with various backbones. We also looked at how well the standard Machine Learning (ML) technique, Neural Network (NN) approaches, U-Net, performed in fruit detection. The following conclusions were drawn based on empirical findings: In the plantation, we discovered a viable deep learning system for fruit detection. The proposed approach can extract deeper fruit characteristics while reducing background and uneven fruit influence |
| 7. Acknowledgement | 8. Reference |
|
I would like to thank my teachers Prashant Pal, Shashank Kumar, yogesh kumar, and Saurabh Bhansod, for their guidance and support in completing my project and research paper on "Evaluation and Segregation of Fruit Quality using Machine and Deep Learning Techniques." Their expertise and encouragement were invaluable in shaping my understanding of the topic. I am also grateful to my colleagues and peers who provided feedback and suggestions, improving the project's quality. Lastly, I thank the institutions and organizations that provided resources and infrastructure for the research. Thank you all for contributing to the successful completion of this project and publication of the research paper |
|
 |
|
