MUCKE aims to mine a large volume of images, to structure them conceptually and to use this conceptual structuring in order to improve large-scale image retrieval. The last decade witnessed important progress concerning low-level image representations. However, there are a number problems which need to be solved in order to unleash the full potential of image mining in applications. The central problem with low-level representations is the mismatch between them and the human interpretation of image content. This problem can be instantiated, for instance, by the incapability of existing descriptors to capture spatial relationships between the concepts represented or by their incapability to convey an explanation of why two images are similar in a content-based image retrieval framework. We start by assessing existing local descriptors for image classification and by proposing to use co-occurrence matrices to better capture spatial relationships in images. The main focus in MUCKE is on cleaning large scale Web image corpora and on proposing image representations which are closer to the human interpretation of images. Consequently, we introduce methods which tackle these two problems and compare results to state of the art methods. Note: some aspects of this deliverable are withheld at this time as they are pending review. Please contact the authors for a preview.

http://ieeexplore.ieee.org/iel2/4524/12820/00592460.pdf

Image Processing

India is the second largest producer of fruits after China. Due to the lack of skilled workers, 30–35% of the harvested fruits is wasted. Again, because of human perception subjectivity identification, classification and grading of fruits not done precisely. So, it is required to impose the automation system in the fruit industry. The machine learning techniques with adequate concepts of image processing have a great scope to provide intelligence for designing an automation system to differentiate the fruits according to its type, variety, matureness and intactness. This paper presents a brief analysis of techniques proposed in the research articles in the year 2010 to 2019, with a focus on the development of state of the art. The related studies are compared with different techniques for identification, classification and grading of fruits. This paper also outlines the current achievements, limitations, and suggestions for future research.

Identification, classification & grading of fruits using machine learning & computer intelligence: a review

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

Machine vision for the maturity classification of oil palm fresh fruit bunches based on color and texture features

The agriculture being the major source of revenue for the people in the rural areas in a country like India many measures have been taken to improve the revenue of the farmers. The assessing the ripeness of the fruits is also one of the primary responsibilities of the farmer to fix the proper time to glean the fruits and taking them to the market. Computer vision and the image processing together remains as a key methodology in reducing the human labor and classifying the different stages of maturity is has become very prominent in examining the stages of the fruit growth. As the color seems to be the important feature to be observed in determining the different stages of the fruits maturity and color identification of the tropic fruits is difficult due to the various illuminations and the partial clogging up of the fruits. In order to identify maturity stage of the fruits the paper proposes a RGBD analysis to examine the stages of the fruits and identify the various stages of maturity.

https://www.irojournals.com/iroiip/V1/I2/06.pdf

Sanjida Akther Jerin

Papers

Automatic detection of mango ripening stages – An application of information technology to botany