Object Detection and Recognition for a Pick and Place Robot Rahul Kumar The University of the South Pacific Suva, Fiji Email: rahul.kumar@usp.ac.fj Sanjesh Kumar The University of the South Pacific Suva, Fiji Email: s11065712@student.usp.ac.fj Sunil Lal The University of the South Pacific Suva, Fiji Email: sunil.lal@usp.ac.fj Praneel Chand The University of the South Pacific Suva, Fiji Email: chand_pc@usp.ac.fj Abstract—Controlling a Robotic arm for applications such as object sorting with the use of vision sensors would need a robust image processing algorithm to recognize and detect the target object. This paper is directed towards the development of the image processing algorithm which is a pre-requisite for the full operation of a pick and place Robotic arm intended for object sorting task. For this type of task, first the objects are detected, and this is accomplished by feature extraction algorithm. Next, the extracted image (parameters in compliance with the classifier) is sent to the classifier to recognize what object it is and once this is finalized, the output would be the type of the object along with it’s coordinates to be ready for the Robotic Arm to execute the pick and place task. The major challenge faced in developing this image processing algorithm was that upon making the test subjects in compliance with the classifier parameters, resizing of the images conceded in the loss of pixel data. Therefore, a centered image approach was taken. The accuracy of the classifier developed in this paper was 99.33% and for the feature extraction algorithm, the accuracy was 83.6443%. Finally, the overall system performance of the image processing algorithm developed after experimentation was 82.7162%. Keywords – Object Detection, Object Recognition, Feature Extraction, Classifier. I. INTRODUCTION Vision based control of the robotic system is the use of the visual sensors as a feedback information to control the operation of the robot. Integration of the vision based algorithms can enhance the performance and the efficiency of the system. Vision based configurations have been implemented to mimic human visual sensors. Orienting towards robotic arms, object recognition is vital for the operation of arms for navigation and grasping tasks. Often it has been the case that image processing (IP) algorithms require huge processing time for the successful implementation of object recognition. The work presented in [1] critically explains the basic algorithms to be addressed before applying image processing techniques. These techniques include; image enhancement, noise reduction and a visual loop algorithm (based on trial and error approach). Moreover, the works of [2], [3] and [4] presents the IP algorithms and approaches to reduce response time and increase in the efficiency for the object recognition tasks. In [8], discussion is based on the reduction of computation time using Trainarp algorithm (derived from ANN). It also presents the method to migrate from the statistical approach to Artificial Neural Networks (ANN). The author has stated the efficiency as 95% and response time of 94ms. Likewise, [3] has conversed on employing a parallel programming approach called object surface reconstruction method. Upon comparison with serial approach, parallel programming method is ten times faster. To reduce cost and improve on performance, [4] has presented the communication of vision system via USB. The vision system used was a webcam for which via MATLAB, the system is enabled to perceive environment through artificial vision via IP algorithms. Along with the classification part, the concept of Feature Extraction (FE) is also studied. FE mostly acts as a pre- processing algorithm to furnish the dataset for the classifier to make important decisions/classification. The work of [5] elaborated on the usage of multi-stereo vision technique for the detection of 3D Object. Eliminating the background i.e. objects of least interest, using opening and closing morphological techniques, 3D detection of a particular object was achieved. Similarly, [6] conversed about one of the Robust Object detection algorithm. This algorithm is known as the Viola-Jones IP method, a state of the art face detector. The robustness of this algorithm was due to cascaded architecture of the strong classifiers arranged in the order of complexity. This approach was incorporated to reduce the processing time. Lastly, feature extraction via Contour matching is also one of the best methods to detect objects [7]. The trained shape is matched according to a probabilistically motivated distance measure which enhances the shape comparisons within the framework. The works in [7] also presented on the noise reduction and other image optimization via segmentation and other IP techniques.