Scribd
Upload
29 views4 pages

Assignment 1

Uploaded by

prema
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF or read online on Scribd
29 views4 pages

Assignment 1

Uploaded by

prema
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF or read online on Scribd
You are on page 1/ 4
Abstract: In the agricultural sector, automation is a useful tool that helps to improve the production, quality and economic growth of the country. One of the essential tasks that farmers have to do is to grade their fruits based on their features. This task has a significant impact on how the fruits are evaluated for quality and exported to other markets. Human grading and sorting is not an efficient way to do this task, as it has many drawbacks. Itis a slow process that takes a lot of time and effort. It is also prone to errors and mistakes that can affect the accuracy and reliability of the grading. It is also a tedious and boring process that can reduce the motivation and satisfaction of the workers. Therefore, there is a need for a smart fruit grading system that can overcome these challenges. Many researchers have been working on developing different algorithms for fruit sorting using computer vision Computer vision is a field of artificial intelligence that deals with processing and analyzing images and videos. The most common features that researchers use to sort fruits using computer vision are color, texture and shape. These features help them to identify the diseases, maturity and class of the fruits. For example, color can indicate the ripeness or freshness of the fruit, texture can indicate the smoothness or roughness of the skin, and shape can indicate the size or deformity of the fruit. These features are then used to train a network based on soft computing techniques. Soft computing techniques are methods that can deal with uncertainty, imprecision and complexity in data. They can learn from data and adapt to changes. Some examples of soft computing techniques are neural networks, fuzzy logic and genetic algorithms. Objectives: A fruit processing plant wants to automate the process of sorting incoming fruits (apple, orange) according to their shape, size, color, lightness etc. The automation system consists of: 4. A conveyor belt for incoming product. 2, Two conveyor belt for sorted product. 3. A pick-and-place robotic arm. 4. Avision system with an overhead CCD camera. 5. A computer to analyze images and control the robotic arm Problem Analysis: Set up a camera and take some sample images to extract features: Shape Color Size Lightness Edges These are the set of all suggested features to explore for use in our classifier. Preprocessing: Use a segmentation operation to isolate fishes from one another and from the background. « Information from a single fish is sent to a feature extractor whose purpose is to reduce the data by measuring certain features « The features are passed to a classifier. Preprocessing | Feature extraction | l Classification LN Apple Orange Figure: Fruits classification Features Extraction: To classify apples and oranges using computer vision, you need to extract relevant features from the images of these fruits that can be used for classification. Feature extraction is a crucial step in the process. Here are some common features that can be extracted for the classification of apples and oranges: 1. Color Features: © Color Histogram: Calculate the color histograms (RGB or HSV) to represent the distribution of color intensities in the image. * Average Color: Compute the average color of the fruit, which can help distinguish the characteristic color of apples (usually red or green) from oranges (typically orange). Texture Features: * Texture Histogram: Use texture descriptors like Local Binary Patterns (LBP) or Gabor filters to capture the texture patterns on the fruit's surface. * Co-occurrence Matrix: Calculate texture features based on the gray-level co-occurrence matrix (GLCM) to quantify texture regularity. . Shape and Size Features: * Aspect Ratio: Measure the ratio of the major axis length to the minor axis length of the fruit to capture differences in shape. * Circularity: Calculate the circularity of the fruit to distinguish between round oranges and the more oval-shaped apples. Geometric Features: * Centroid Location: Determine the centroid of the fruit, which can help identify its position and orientation in the image. * Elongation: Calculate the elongation of the fruit, which can be used to differentiate between the two. Edge Features: © Edge Histogram: Analyze edge features by creating an edge histogram or using techniques like the Canny edge detector to identify the edge characteristics. Classification: 1. Model Selection: Choose a machine learning or deep learning model for classification. Several options are available: * Traditional Machine Learning: You can use classifiers like Support Vector Machines (SVM), Random Forests, k-Nearest Neighbors, or Naive Bayes. * Deep Learning: Convolutional Neural Networks (CNNs) are powerful for image classification and are commonly used in modern computer vision tasks. 2. Model Training: * Train the selected model on the training dataset using the extracted features. © Fine-tune hyper-parameters as necessary to achieve the best performance * Monitor the model's performance on the validation set to prevent overfitting. 3. Model Evaluation: * Evaluate the trained model's performance on the testing dataset using metrics like accuracy, precision, recall, and F1 score. * Analyze the model's confusion matrix to understand its performance on classifying apples and oranges.

You might also like