Literature Review : Fruit Recognition System ( Fruitcognizer )

These 16 features included 12 features calculated based on the 6 multispectral bands, which is mean value and standard deviation of these bands. In addition, we chose intensity, texture-variance, texture-mean, and NDVI (Normalized Difference Vegetation Index) for classifications. Finally, training samples were selected for each classification category based on the previously segmented and merged objects

Fresh Fruits Color and variety are important, and in the Mediterranean outdoor markets are common so people have easy access to large selections of fresh produce.

One fruit that caught my eye was a cucumber. I love cucumbers. Cucumbers are my favorite thing to eat! Cucumbers go with anything. They’re so easy to eat but not so easy to grow! You have to grow cucumbers in a warm climate too hot or to cold of a climate can stress the crop out. You have to mulch cucumbers above 70 degrees or they’ll get stressed out and die. You have to handle cucumbers very carefully or they’ll get stressed out. You would have to regulate the crop very carfully! They need tons of sunlight and plenty of water. The cucumber also needs good soil and fertilizer. Like people they can be very picky. You also have to kill the weeds that are by the cucumber.

This would enable supervised classification of melanocytic lesions. The melanoma detection process is composed of following steps that are the preprocessing, the segmentation, the feature extraction and feature selection ,thereby improving the classification

Visually impaired people face a lot of problems in their daily life. In order to make them live confidentially without the need of others we develop an assistive technology. We propose a camera based tool which helps to read the text label from the products that are commonly in use. We first propose image capturing method that is usually a camera used to capture the object whose label is to be read. Then feature extraction, every image has its own features different from others. We use certain feature extraction algorithms like gradient conversion, sobel edge detection, canny edge detection etc. Histogram might be applied to extract the image features. Finally speech output the processed image after recognition label text is output to visually impaired people as speech output. Raspberry pi is used for this entire application.

Average annual precipitation of experimental site over last ten year was 1200 -1800 mm. Terminal leaf length, terminal leaf width, terminal petiole length, petal length, petal width, flower diameter, fruit length, fruit width has been measured in centimetres. Number of days from Julian Day (1st January) to 5% bud burst have been counted and expressed as days to bud burst. Similarly, number of days from Julian Day to 95% bud burst have been counted and expressed as days to end bud burst. Weight of ten representative fruits of different sizes has been recorded with the help of electronic pan balance and average is expressed as fruit weight (g). Volume of fruits has been measured by dipping the fruits in measuring cylinder and measuring the volume of water replaced by fruits. Fully ripe fruits were used to measure the pH of juice by pH meter. Total soluble solids at full ripe stage (ready to eat) have been measured with the help of the refractometer and expressed as

Tested for a number of datasets and it is found that accuracy of image recognition for proposed approach is higher. The results are evaluated for different resolutions of the image and it is found that even for low resolution accuracy is considerably more for proposed approach.

Local Binary Patterns (LBP) is on of well-know descriptor used for pattern recognition \cite{G1}. LBP describes textures features of the image. It divided into two different descriptors: (1) local descriptors and (2) global descriptor. The global descriptor used for separating the non objects blocks, while the local provides detailed objects information which can be used in recognition application. It is mathematically calculated through dividing the image into blocks and computing the texture histogram for each block.\par

In this paper, we are going to develop real time application on college student for automatic detection and recognition of student during academics, followed by display of personal information of students. This application makes proper use of CCTV camera for real time face detection of students of particular college. The proposed application can be divided into four major steps. In first step, each person in the image is detected. In the second step, a face detection algorithm detects faces of each person. In third step, we use a face recognition algorithm to match the faces of persons in the captured image with the database of students’ faces which also stores personal as well as academic information of each student. In final step, the face of student along with his/her personnel information will be displayed on screen to the user when the image captured by CCTV camera contains any student image of present college. The college administrator as well as faculty members can use this application to identify students and also to distinguish students from outsiders.

Implementation of any system needs the study of features, it may be symbolic, numerical or both. An example of a symbolic feature is color; an example of numerical feature is weight. Features may also result from applying a text extraction algorithm or operator to the input data. The related problems of feature selection and feature extraction must be addressed at the outset of any text recognition system design. The key is to choose and to extract features that are computationally feasible and reduce the problem data into a manageable amount of information without discarding valuable information.

In this paper, we will be looking at different methods for comparative study of the state of the art image processing techniques stated below (K means clustering, wavelet transforms and DiVI approach) which consider attributes like color, shape and texture for image retrieval which helps us in solving the problem of managing image databases easier.

Abstract- In this paper, we are going to develop real time application on college student for automatic detection and recognition of student during academics, followed by display of personal information of students. This application makes proper use of CCTV camera for real time face detection of students of particular college. The proposed application can be divided into four major steps. In first step, each person in the image is detected. In the second step, a face detection algorithm detects faces of each person. In third step, we use a face recognition algorithm to match the faces of persons in the captured image with the database of students’ faces which also stores personal as well as academic information of each student. In final step, the face of student along with his/her personnel information will be displayed on screen to the user when the image captured by CCTV camera contains any student image of present college. The college administrator as well as faculty members can use this application to identify students and also to distinguish students from outsiders.

The world has been confronted with serious difficulties in curbing down the rate of undernourishment especially in sub-Sahara Africa (Vinceti et al., 2013, Arnold et al., 2011, Goenster et al., 2011). In developing countries, the livelihood and food security of smallholder land users are often at risk from unpredictable harvests, land degradation and climate change (Paumgarten and Shackleton, 2011, Mertens et al., 2000, Ndoye and Kaimowitz, 2000, Sunderlin et al., 2000). Of about one billion hungry people, 98% live in developing countries. Seventy percent of chronically hungry people are smallholder farmers, 43% of total farmers worldwide are women and 38% of youths in Africa are working in agriculture (Conway and Wilson, 2012, FAO, 2011). For instance, in forest areas of Cameroon, stunting and chronic malnutrition was experienced by 30.3% of children between 24-47 months in the South region and 27.8% in the Centre region (Socpa et al., 2008). Since the varieties of fruits are quite many (Matig et al., 2006, van-Wyk, 2005) and vary from one season and climatic region to another, fruits and wild foods can constitute important sources of food (Vinceti et al., 2013, Termote et al., 2012, Ingram and Shure 2010, Nesbit et al., 2010, Shackleton and Shackleton, 2004) during food scarcity. Thus, fruits can serve as safety nets (Paumgarten and Shackleton, 2011) in the

Various classification methods have been developed to extract information from imageries. The two main types are pixel and object-based methods. Pixel-based methods can be cluster based unsupervised or supervised classification whereas the later uses statistical (e.g., maximum likelihood algorism) and non-statistical algorithms (e.g., support vector machines) (Lu, Li, Kuang, & Moran, 2014). The object-based classification which overcomes some of the particular problems encountered with pixel-based classification (Blaschke, 2010) was used to analyze

Abstract— This paper proposed two set of edge-texture features is such as Discriminative Robust Local Binary Pattern (DRLBP) and Discriminative Robust Local Ternary Pattern (DRLTP) for object recognition. The proposed DLBP and DRLTP are resultant from the disadvantage of the Local Binary Pattern (LBP), Local Ternary Pattern (LTP) and Robust LBP (RLBP).The LBP system and the RLBP system are mapped in the same block .The proposed feature indentifies the problem of discrimination between a bright object against dark background and vice-versa. The proposed feature also retains contrast information for object contours the LBP, LTP and RLBP discards. By the proposed features the objects is further analyzed for the accurate position of the object in the given image.