One of the important quality features of fruits is its appearance. Appearance not only influences their market value, the preferences and the choice of the consumer, but also their internal quality to a certain extent. Color, texture, size, shape, as well the visual flaws are generally examined to assess the outside quality of food. Manually controlling external quality control of fruit is time consuming and laborintensive. Thus for automatic external quality control of food and agricultural products, computer vision systems have been widely used in the food industry and have proved to be a scientific and powerful tool for by intensive work over decades. The use of machine and computer vision technology in the field of external quality inspection of fruit has been published based on studies carried on spatial image and / or spectral image processing and analysis. A detailed overview of the process of fruit classification and grading has been presented in this paper. Detail examination of each step is done. Some extraction methods like Speeded Up Robust Features (SURF), Histogram of Oriented Gradient (HOG) and Local Binary Pattern (LBP) are discussed with the common features of fruits like color, size, shape and texture. Machine learning algorithms like K-nearest neighbor (KNN), Support Vector Machine (SVM), Artificial Neural Networks (ANN) and Convolutional Neural Networks (CNN) are also discussed. Process, advantages, disadvantages, challenges occurring in food-classification and grading is discussed in this paper, which can give direction to researchers. General Terms Machine Vision, Fruit Classification, Grading.

/pdf/machine-vision-based-fruit-classification-and-grading-a-4iwbyvs4nn.pdf

Machine Vision based Fruit Classification and Grading - A Review

Automatic green fruit counting in orange trees using digital images

https://eprints.ncl.ac.uk/file_store/production/253823/82F670EC-7309-47EC-8C44-569DBB61D681.pdf

Automatic scoring of lateral and sternal lying posture in grouped pigs using image processing and Support Vector Machine

A microcontroller based machine vision approach for tomato grading and sorting using SVM classifier

Detection of aggressive behaviours in pigs using a RealSence depth sensor

Shape and weight grading of mangoes using visible imaging

The conventional method of grading Harumanis mango is time-consuming, costly and affected by human bias. In this research, an in-line system was developed to classify Harumanis mango using computer vision. The system was able to identify the irregularity of mango shape and its estimated mass. A group of images of mangoes of different size and shape was used as database set. Some important features such as length, height, centroid and parameter were extracted from each image. Fourier descriptor and size-shape parameters were used to describe the mango shape while the disk method was used to estimate the mass of the mango. Four features have been selected by stepwise discriminant analysis which was effective in sorting regular and misshapen mango. The volume from water displacement method was compared with the volume estimated by image processing using paired t-test and Bland-Altman method. The result between both measurements was not significantly different (P > 0.05). The average correct classification for shape classification was 98% for a training set composed of 180 mangoes. The data was validated with another testing set consist of 140 mangoes which have the success rate of 92%. The same set was used for evaluating the performance of mass estimation. The average success rate of the classification for grading based on its mass was 94%. The results indicate that the in-line sorting system using machine vision has a great potential in automatic fruit sorting according to its shape and mass.

/pdf/in-line-sorting-of-harumanis-mango-based-on-external-quality-3tetno5xqa.pdf

In-Line Sorting of Harumanis Mango Based on External Quality Using Visible Imaging

This paper highlights on the development of a Ultrasonic Sensor Bank with sixteen pieces 40 kHz ultrasonic sensor (USB-16) mounted on hexadecagon-based plate on a mobile robot to perform real time 2D and 3D mapping. The purpose of this research is to evaluate the capability of USB-16 in providing an accurate map in terms of the walls perimeter and its shape, where the robot is located. Each wall will be scanned with USB-16 sensor bank to measure the distance between the center of sensor bank and the wall. The Homogeneous Transformation Matrix (HTM) and trigonometrically algorithm is utilized in this research as a wall mapping algorithm and is clearly explained in this paper. An optimum wall mapping algorithm was introduced to minimize measurement error. The optimum wall mapping technique named a Nominal Wall Angle (NWA) using trigonometric approach was introduced to improve the mapping accuracy. This algorithm has the capability to improve the ultrasonic mapping accuracy during the scanning process and is different from data manipulation technique like most of similar researches currently adapted. The comparison of experimental results before and after implementation of the optimization technique in different wall shape (Curve, Square, Rectangle, Triangle and Laboratory environment) will be presented in this paper. The results are very impressive, where the implementation of NWA algorithm is able to produce an accurate wall mapping compared with the actual wall size. LabVIEW software, Basic Atom and BASIC Stamp microcontroller are fully utilized to produce the real time 2D and 3D graph during the USB-16 mapping.

A novel indoor mobile robot mapping with USB-16 ultrasonic sensor bank and NWA optimization algorithm

Weedy rice infestation has become a major problem in all rice-growing countries, especially in Malaysia. Challenges remain in finding a rapid technique to identify the weedy rice seeds that tend to pose similar taxonomic and physiological features as the cultivated rice seeds. This study presents image processing and machine learning techniques to classify weedy rice seed variants and cultivated rice seeds. A machine vision unit was set up for image acquisition using an area scan camera for the Red, Green and Blue (RGB) and monochrome images of five cultivated rice varieties and a weedy rice seed variant. Sixty-seven features from the RGB and monochrome images of the seed kernels were extracted from three primary parameters, namely morphology, colour and texture, and were used as the input for machine learning. Seven machine learning classifiers were used, and the classification performance was evaluated. Analyses of the best model were based on the overall performance measures, such as the sensitivity, specificity, accuracy and the average correct classification of the classifiers that best described the unbalanced dataset. Results showed that the best optimum model was developed by the RGB image using the logistic regression (LR) model that achieved 85.3% sensitivity, 99.5% specificity, 97.9% accuracy and 92.4% average correct classification utilising all the 67 features. In conclusion, this study has proved that the features extracted from the RGB images have higher sensitivity and accuracy in identifying the weedy rice seeds than the monochrome images by using image processing and a machine learning technique with the selected colour, morphological and textural features.

/pdf/weedy-rice-classification-using-image-processing-and-a-2kds7r9u.pdf

Weedy Rice Classification Using Image Processing and a Machine Learning Approach

This paper describes the usage of sixteen piece 40 kHz ultrasonic sensors, known as Ultrasonic Sensor Bank (USB-16) mounted on a mobile robot platform. The Homogeneous Transformation Matrix (HTM) and trigonometric algorithm is utilized in this research as a wall mapping algorithm. The walls were designed with four types of basic shapes such as rectangle, triangle, curved and square, which are rarely tested by researchers in real time. Mapping and localization within real laboratory environment was also conducted. In this research, the USB-16 sensor bank transmitted ultrasonic signals in frequency waveform to the wall; the reflected signal was then filtered by a Nominal Wall Angle (NWA) algorithm to optimize the accuracy of the measured data. The purpose of this research is to determine the capability of USB-16 in not only providing an accurate map, but also its capability to recognize shapes and localization during mapping based on the size of walls. Next, NWA and KNN algorithm were applied in this experiment to study the accuracy of localization algorithm. This experiment had been carried out with two types of data sets, distance and coordinates. With the combination of these algorithms, the system can improve the accuracy of localization from 80% to 90% for basic wall shape and 78% for real laboratory environment. Basic Stamp, Basic Atom, LabVIEW and MATLAB software were fully utilized in the Self Localization and Mapping problem.

M. F. Ibrahim

Papers

Shape and weight grading of mangoes using visible imaging

In-Line Sorting of Harumanis Mango Based on External Quality Using Visible Imaging

A novel indoor mobile robot mapping with USB-16 ultrasonic sensor bank and NWA optimization algorithm

Weedy Rice Classification Using Image Processing and a Machine Learning Approach

Indoor mobile robot localization using KNN