No abstract

In this paper, an efficient approach has been proposed to localize every clearly visible object or region of object from an image, using less memory and computing power. For object detection we have processed every input image to overcome several complexities, which are the main limitations to achieve better result, such as overlap between multiple objects, noise in the image background, poor resolution etc. We have also implemented an improved Convolutional Neural Network based classification or recognition algorithm which has proved to provide better performance than baseline works. Combining these two detection and recognition approaches, we have developed a competent multi-class Fruit Detection and Recognition (FDR) model that is very proficient regardless of different limitations such as high and poor image quality, complex background or lightening condition, different fruits of same shape and color, multiple overlapped fruits, existence of non-fruit object in the image and the variety in size, shape, angel and feature of fruit. This proposed FDR model is also capable of detecting every single fruit separately from a set of overlapping fruits. Another major contribution of our FDR model is that it is not a dataset oriented model which works better on only a particular dataset as it has been proved to provide better performance while applying on both real world images (e.g., our own dataset) and several states of art datasets. Nevertheless, taking a number of challenges into consideration, our proposed model is capable of detecting and recognizing fruits from image with a better accuracy and average precision rate of about 0.9875.

No abstract

No abstract

Object detection from a real-time image is gaining increasing research interest in recent years as it can substantially facilitate a wide range of content-based multimedia applications. Detecting objects from real time image with fine grained details requires extensive amount of preprocessing, computation and time. In addition, multi category object detection is a very complex and diverse problem domain. Some traditional object detection and recognition models previously train their model with huge number of rich and highly annotated images and then divide an input image into set of bounding boxes and calculate the confidence score for each object category in the image. Most of the existing approaches require huge amount of time and computation for object detection. On the other hand, some models only work with local images where image has a single, focused and center-based object. In order to overcome such limitations of existing models, we are proposing a Region of Interest (ROI) based object detection model. In our proposed work, instead of using a fixed number of bounding boxes (e.g. n×n) or working with local images, our model identifies all the ROI at any location of the image. We have tested our algorithm on a number of benchmark datasets for fine-grained object detection. In our work, we have demonstrated significant efficiency as well as accuracy in term of object detection. We have significantly improved the algorithm to detect object irrespective of location, number of object in the image, object overlapping and minuscule objects. Our proposed model can reduce the noise in an image, and thereby, can identify ROI even from poor quality image, noisy background, irrelevant context and misleading feature. To demonstrate the accuracy of our proposed algorithm we have introduced a feature matching approach to identify the detected objects correctly.