The ImageCLEF 2012 Plant Identification Task

2014

Our aim is to implement a plant identification application that can run on smartphones, and this shared task includes it. After the plant identification task of 2013 we concluded that the most frequent trees (e. g. in Hungary) can be identified well by a leaf, when there is a white paper background behind it at the time of photographing. This is why we want to classify more accurately this kind of pictures. Our other important goal is to develop a system which can be trained online while smartphone users take more and more photos. In the previous year there was a separate shared task for the 'Sheet as Background' photos, how- ever this year the task is very complex, and supposes solutions for hard image processing problems, not just feature extraction and classification solutions.

2012

This paper describes the participation of Inria IMEDIA2 Team, within the Pl@ntNet project 4 , at the ImageCLEF2012 plant identification task. The runs used very distinct approaches, sometimes relying on similar extracted features. For Scan and Scan-like categories, the first two runs combine distinct local and contour approaches in two ways (late and early fusion), while the third run explores the learning capacity of a multi-class SVM technique on a contour based descriptor. For Photograph our runs used local features positioned towards the center of the image to reduce the impact of background features. In the second run, an automatic segmentation with a rejection criterion was attempted. In the third run, points were associated with interesting zones. In general, even if they were distinct, the methods used performed very well.

The continuously growing amount of multimedia content has enabled the application of image content retrieval solutions to different domains. Botanical scientists are working on the classification of plant species in order to infer the relevant knowledge that permits them going forward in their environmental researches. The manual annotation of the existing and newly creation plants datasets is an outsized task that is becoming more and more tedious with the daily incorporation of new images. In this paper we present an automatic system for the identification of plants based on not only the content of images but also on the metadata associated to them. The classification has been defined as a classification plus fusion solution, where the images representing different parts of a plant have been considered independently. The promising results bring to light the chances of the application computer vision solutions to botanical domain.

2011

We describe our participation in the plant identification task of ImageClef 2011. Our approach employs a variety of texture, shape as well as color descriptors. Due to the morphometric properties of plants, mathematical morphology has been advocated as the main methodology for texture characterization, supported by a multitude of contour-based shape and color features. We submitted a single run, where the focus has been almost exclusively on scan and scan-like images, due primarily to lack of time. Moreover, special care has been taken to obtain a fully automatic system, operating only on image data. While our photo results are low, we consider our submission successful, since besides being our first attempt, we rank 1 st considering the average of the scan and scanlike results, upon which we had concentrated our efforts.

2014

This paper describes the participation of Inria within the Pl@ntNet project 7 at the LifeCLEF2014 plant identification task. The aim of the task was to produce a list of relevant species for each plant observation in a test dataset according to a training dataset. Each plant observation contains several annotated pictures with organ/view tags: Flower, Leaf, Fruit, Stem, Branch, Entire, Scan (exclusively of leaf). Our system treated independently each category of organ/view and then a late hierarchical fusion is used in order to combine the results on visual content analysis from the most local level analysis in pictures to the highest level related to a plant observation. For the photographs of flowers, leaves, fruits, stems, branches and entire views of plants, a large scale matching approach of local features extracted using different spatial constraints is used. For scans, the method combines the large scale matching approach with shape descriptors and geometric parameters on shape boundary. Then, several fusion methods are experimented through the four submitted runs in order to combine hierarchically the local responses to the final response at the plant observation level. The four submitted runs obtained good results and got the 4th to the 7th place over 27 submitted runs by 10 participating teams.

2012

We describe our participation in the plant identification task of ImageClef 2012. We submitted two runs, one fully automatic and another one where human assistance was provided for the images in the photo category. We have not used the meta-data in either one of the systems, for exploring the extent of image analysis for the plant identification problem. Our approach in both runs employs a variety of shape, texture and color descriptors (117 in total). We have found shape to be very discriminative for isolated leaves (scan and pseudoscan categories), followed by texture where mathematical morphology has been our main methodology. While we have used color, we did not found color information to be very useful. Mathematical morphology is also used in the watershed algorithm used for segmentation, in slightly different forms for automatic and human assisted systems. Our systems have obtained the best overall results in both the automatic and manual categories, with 43% and 45% identification accuracies respectively. We have also obtained the best results on the scanned image category, with 58% accuracy, while the 2nd best system had a 49% accuracy.

2010

We present a content-based image retrieval system for plant identification which is intended for providing users with a simple method to locate information about their house plants. A plant image consists of a collection of overlapping leaves and possibly flowers, which makes the problem challenging. We studied the suitability of various well-known color, texture and shape features for this problem, as well as introducing some new ones. The features are extracted from the general plant region that is segmented from the background using the max-flow min-cut technique. Results on a database of 132 different plant images show promise (in about 72% of the queries, the correct plant image is retrieved among the top-15 results).

Our aim is to implement a plant identification application that can run on smartphones, and this shared task includes it. After the plant identification task of 2013 we concluded that the most frequent trees (e. g. in Hungary) can be identified well by a leaf, when there is a white paper background behind it at the time of photographing. This is why we want to classify more accurately this kind of pictures. Our other important goal is to develop a system which can be trained online while smartphone users take more and more photos. In the previous year there was a separate shared task for the 'Sheet as Background' photos, however this year the task is very complex, and supposes solutions for hard image processing problems, not just feature extraction and classification solutions.

AoB PLANTS

There has been a recent explosion in development of image recognition technology and its application to automated plant identification, so it is timely to consider its potential for field botany. Nine free apps or websites for automated plant identification and suitable for use on mobile phones or tablet computers in the field were tested on a disparate set of 38 images of plants or parts of plants chosen from the higher plant flora of Britain and Ireland. There were large differences in performance with the best apps identifying >50 % of samples tested to genus or better. Although the accuracy is good for some of the top-rated apps, for any quantitative biodiversity study or for ecological surveys, there remains a need for validation by experts or against conventional floras. Nevertheless, the better-performing apps should be of great value to beginners and amateurs and may usefully stimulate interest in plant identification and nature. Potential uses of automated image recognit...