Online ISSN: 2515-8260

Keywords : object detection

Identification and Detection of Plant Diseases by Convolutional Neural Networks

A. Iyswariya; V. Ramkumar; Sarvepalli Chandrasekhar; Yaddala Chandrasekhar Reddy; Vunnam Sai Tathwik; V.Praveen Kumar

European Journal of Molecular & Clinical Medicine, 2020, Volume 7, Issue 4, Pages 2200-2205

Agribusiness is the foundation of Indian economy. Plant health and food safety goes hand in hand. The health of green plants is of vital importance to everyone.Plant diseases being an impairment to the normal state of a plant, it interrupts or modifies plants vital functions. The proposed system helps in identification of plant disease and provides remedies that can be used as a defense mechanism against the disease. The database obtained from the Internet is properly segregated and the different plant species are identified and are renamed to form a proper database then obtain test-database which consists of various plant diseases that are used for checking the accuracy and confidence level of the project .Then using training data we will train our classifier and then output will be predicted with optimum accuracy. We use Convolution Neural Network (CNN) which comprises of different layers are used for prediction.CNNs provide unparalleled performance in tasks related to the classification and detection of crop diseases. They are able to manage complex issues in difficult imaging conditions A prototype drone model is also designed which can be used for live coverage of large agricultural fields to which a high resolution camera is attached and will capture images of the plants which will act as input for the software, based of which the software will tell us whether the plant is healthy or not. With our code and training model we have achieved an accuracy level of 78%. Our software gives us the name of the plant species with its confidence level and also the remedy that can be taken as a cure.

Object Detection classifier using Faster R-CNN Algorithm

Thilagavathy A; Rishikesh S; Yuva Prasad C; Pradeep Kumar S

European Journal of Molecular & Clinical Medicine, 2020, Volume 7, Issue 4, Pages 2087-2096

In this paper,we have done image processing as a project to identify an object. In order to find the unlabeled data with images, we proposed the project with the Faster-RCNN-v2-COCO model. This is processed by convolution neural network model with the region proposal network (RPN) method labeled data has been trained to learn the object of a particular image. This algorithm proposed for faster accuracy and better performance in detection by training N number of labeled data. Moreover, the error propagated during the training phase is reduced by including several pseudo annotations that are generated in the previous training phase. The result of the experiment reveals Currency detection, Signal detector, real time household objects are basic applications that are developing by object detection.

Real time object detection using Image Processing

Dr .S.Joshua Kumaresan; Shaik Shameem; M. Priyadharshini; Mr. Vinodh James; R.Lakshmi Priya

European Journal of Molecular & Clinical Medicine, 2020, Volume 7, Issue 4, Pages 2403-2411

Object detection plays an important role in real time applications. It is used in many applications such as surveillance monitoring, human machine interaction, army base etc. The main aim of this paper is to detect the object and to detect the colour of the object using Image processing technique. Pi camera. Raspberry pi 11 kit interfaced with pi camera is used for detection of object. Raspbian os with python coding is used for object detection and colour recognition.

Automatic detection of satellite images using blob detection and boundary tracking techniques

Abhay Chaturvedi; Aasheesh Shukla

European Journal of Molecular & Clinical Medicine, 2020, Volume 7, Issue 4, Pages 524-530

Automatic detection of vehicles data has been widely used in the area of traffic surveillance system where the efficient traffic management along with safety is the main concept. This project depicts the count of the vehicles present at that particular area of traffic using the data provided by the satellite. The satellite captures the image of the particular traffic junction. This satellite image is further processed in order to find the count of the vehicles. The image contains unwanted objects along with the vehicles. For that image, apply thresholding techniques to detect the vehicles and such that unwanted objects whose gray scale values are below the threshold level will be removed. The designed system converts the satellite captured image into gray scale image. This gray scale image is then converted into binary image. It is proposed to develop a unique algorithm for detecting the vehicles using thresholding techniques. If the intensity value is greater than the threshold value, 8-bit of value 255 is assigned else 8-bit of value 0 will be assigned. The edges of the objects present in the binary image will be obtained. Noise will be reduced using filters. The bright areas which are bounded will shows the vehicles present in the image. Boundary formation is useful for detecting the objects in the image. Using Blob detection method, the properties of the objects are depicted and using the Moore Boundary tracking algorithm the boundaries of the objects are detected. Detecting the vehicles and finding the count of the vehicles are the objectives of this project.