Sensors and systems for fruit detection and localization

This paper describes a fruit counting pipeline based on deep learning that accurately counts fruit in unstructured environments. Obtaining reliable fruit counts is challenging because of variations in appearance due to illumination changes and occlusions from foliage and neighboring fruits. We propose a novel approach that uses deep learning to map from input images to total fruit counts. The pipeline utilizes a custom crowdsourcing platform to quickly label large data sets. A blob detector based on a fully convolutional network extracts candidate regions in the images. A counting algorithm based on a second convolutional network then estimates the number of fruits in each region. Finally, a linear regression model maps that fruit count estimate to a final fruit count. We analyze the performance of the pipeline on two distinct data sets of oranges in daylight, and green apples at night, utilizing human generated labels as ground truth. We also show that the pipeline has a short training time and performs well with a limited data set size. Our method generalizes across both data sets and is able to perform well even on highly occluded fruits that are challenging for human labelers to annotate.

Counting Apples and Oranges With Deep Learning: A Data-Driven Approach

Fruit classification using computer vision and feedforward neural network

Automatic classification of fruits via computer vision is still a complicated task due to the various properties of numerous types of fruits. We propose a novel classification method based on a multi-class kernel support vector machine (kSVM) with the desirable goal of accurate and fast classification of fruits. First, fruit images were acquired by a digital camera, and then the background of each image was removed by a split-and-merge algorithm; Second, the color histogram, texture and shape features of each fruit image were extracted to compose a feature space; Third, principal component analysis (PCA) was used to reduce the dimensions of feature space; Finally, three kinds of multi-class SVMs were constructed, i.e., Winner-Takes-All SVM, Max-Wins-Voting SVM, and Directed Acyclic Graph SVM. Meanwhile, three kinds of kernels were chosen, i.e., linear kernel, Homogeneous Polynomial kernel, and Gaussian Radial Basis kernel; finally, the SVMs were trained using 5-fold stratified cross validation with the reduced feature vectors as input. The experimental results demonstrated that the Max-Wins-Voting SVM with Gaussian Radial Basis kernel achieves the best classification accuracy of 88.2%. For computation time, the Directed Acyclic Graph SVMs performs swiftest.

https://www.mdpi.com/1424-8220/12/9/12489/pdf

Classification of Fruits Using Computer Vision and a Multiclass Support Vector Machine

Local ternary co-occurrence patterns: A new feature descriptor for MRI and CT image retrieval

Several fruit recognition techniques are developed based upon color and shape attributes. However, different fruit images may have similar or identical color and shape values. Hence, using color features and shape features analysis methods are still not robust and effective enough to identify and distinguish fruits images. A new fruit recognition system has been proposed, which combines three features analysis methods: color-based, shape-based and size-based in order to increase accuracy of recognition. The proposed method classifies and recognizes fruit images based on obtained feature values by using nearest neighbours classification. Consequently, our system shows the fruit name and a short description to user. The proposed fruit recognition system analysis classifies and identifies fruits successfully up to 90% accuracy. This system also serves as a useful tool in a variety of fields such as education, image retrieval and plantation science.

/pdf/a-new-method-for-fruits-recognition-system-4cvf5th2bo.pdf

A new method for fruits recognition system

Content-based image retrieval techniques have extensively been studied for past few years. However; few systems are dedicated to medical images today while demands for content-based analysis and retrieval tools increases with growth of digital medical image databases. A prototype of content-based image retrieval system is built to investigate performance of descriptors for blood cell image retrieval.Here, traditional global color histogram and wavelet-based method is investigated. In addition, performance of indexing method for the aforementioned descriptors is analyzed. The prototype system allows users to search by providing a query image and selecting one of four implemented methods.Research goal is enhancing current content-based image retrieval techniques. Proposed method is able to perform clinically relevant queries on image databases without user supervision.

A Content-Based Retrieval System for Blood Cells Images

Content-based image retrieval techniques have been extensively studied for the past few years. With the growth of digital medical image databases, the demand for content-based analysis and retrieval tools has been increasing remarkably. Blood cell image is a key diagnostic tool for hematologists. An automated system that can retrieved relevant blood cell images correctly and efficiently would save the effort and time of hematologists. The purpose of this work is to develop such a content-based image retrieval system. Global color histogram and wavelet-based methods are used in the prototype. The system allows users to search by providing a query image and select one of four implemented methods. The obtained results demonstrate the proposed extended query refinement has the potential to capture a user's high level query and perception subjectivity by dynamically giving better query combinations. Color-based methods performed better than wavelet-based methods with regard to precision, recall rate and retrieval time. Shape and density of blood cells are suggested as measurements for future improvement. The system developed is useful for undergraduate education.

Seyed Hadi Mirisaee

Papers

A new method for fruits recognition system

A Content-Based Retrieval System for Blood Cells Images

Evaluation of a Content-Based Retrieval System for Blood Cell Images with Automated Methods