Automatic fruit recognition and counting from multiple images
Automatic fruit recognition and counting from multiple images
复制标题
DOI：
10.1016/j.biosystemseng.2013.12.008
复制
发表时间：
2014-02-01
影响因子：
5.1
通讯作者：
van der Heijden, G. W. A. M.
中科院分区：
文献类型：
--
作者：
Song, Y.;Glasbey, C. A.;van der Heijden, G. W. A. M.
在我们的后基因组世界中，我们被淹没在遗传信息中，科学进步的瓶颈往往是表型分析，即测量生物体的可观察特征，例如计算植物上的果实数量。图像分析是实现自动化的一条途径。在本文中，我们提出了一种方法来识别和计数的水果从图像中杂乱的温室。这些植物是3米高的辣椒，果实形状复杂，颜色各异，类似于植物的树冠。我们的校准和验证数据集包含1000多个实验植物的28，000多张彩色图像。我们描述了一种新的两步方法来定位和计数辣椒果实：第一步是使用词袋模型在单个图像中找到果实，第二步是使用一种新的统计方法对重复的、不完整的观测进行聚类，从而从多个图像中聚集估计值。我们证明，图像分析可能会产生良好的相关性与手动测量（94.6%），我们提出的方法实现了74.2%的相关性，而无需对大型数据集进行任何线性调整。(C)2013年IAgRE。由爱思唯尔有限公司出版。保留所有权利。
In our post-genomic world, where we are deluged with genetic information, the bottleneck to scientific progress is often phenotyping, i.e. measuring the observable characteristics of living organisms, such as counting the number of fruits on a plant. Image analysis is one route to automation. In this paper we present a method for recognising and counting fruits from images in cluttered greenhouses. The plants are 3-m high peppers with fruits of complex shapes and varying colours similar to the plant canopy. Our calibration and validation datasets each consist of over 28,000 colour images of over 1000 experimental plants. We describe a new two-step method to locate and count pepper fruits: the first step is to find fruits in a single image using a bag-of-words model, and the second is to aggregate estimates from multiple images using a novel statistical approach to cluster repeated, incomplete observations. We demonstrate that image analysis can potentially yield a good correlation with manual measurement (94.6%) and our proposed method achieves a correlation of 74.2% without any linear adjustment for a large dataset. (C) 2013 IAgrE. Published by Elsevier Ltd. All rights reserved.