Digital image analysis based automated kiwifruit counting technique

This Paper investigates the use of digital image analysis techniques for developing an automated kiwifruit counting system. Three simple counting methods followed by a minimum distance classifier based segmentation technique in L*a*b colour space were studied. Images were taken prior to harvesting at a New Zealand kiwifruit orchard. Accurate counting of kiwifruit in several sample regions of the orchard is required in order to estimate the fruit harvest. At present, the counting is manually done by hired employees. Manual counting has several issues, such as low accuracy, long duration and higher costs. Automated counting technique facilitates a fast, low cost and potentially more accurate way of counting kiwifruit. Several approaches were trialled and validated on different sets of images. Above 90% accuracy on gold image data and above 60% accuracy on green image data were obtained, showing the potential of using the approach for counting kiwifruit for the harvest estimation purpose. The results, limitations and ongoing research in developing a more robust and consistent technique will be discussed.

1 Introduction

Image analysis based automated counting approaches can be found in many fields, such as medical imaging, horticulture & crop industry and soil research [1], [2] and [3]. They show the efficacy of automated counting systems, which are sufficiently reliable, consistent, fast and also more convenient than manual counting. However there are challenges in developing robust, automated counting techniques and they are unique to the specific problem. Some of the challenges for counting are uneven illumination, noise, occluded objects and clumped objects. For example, Sio, S. W. S. et al. developed a clump splitting technique to address the issue of counting clumped red blood cells [3]. The clumped cells adversely affect the accuracy of the parasitimia, because one clumped cell contains a few cells, but it is counted only once.