Pollution in the form of litter in the natural environment is one of the great challenges of our times. Automated litter detection can help assess waste occurrences in the environment. Different machine learning solutions have been explored to develop litter detection tools, thereby supporting research, citizen science, and volunteer clean-up initiatives. However, to the best of our knowledge, no work has investigated the performance of state-of-the-art deep learning object detection approaches in the context of litter detection. In particular, no studies have focused on the assessment of those methods aiming their use in devices with low processing capabilities, e.g., mobile phones, typically employed in citizen science activities. In this paper, we fill this literature gap. We performed a comparative study involving state-of-the-art CNN architectures (e.g., Faster RCNN, Mask-RCNN, EfficientDet, RetinaNet and YOLO-v5), two litter image datasets and a smartphone. We also introduce a new dataset for litter detection, named PlastOPol, composed of 2418 images and 5300 annotations. The experimental results demonstrate that object detectors based on the YOLO family are promising for the construction of litter detection solutions, with superior performance in terms of detection accuracy, processing time, and memory footprint.
Most pattern classification techniques are focused on solving closed-set problems in which a classifier is trained with samples of all classes that may appear during the testing phase. In many situations, however, samples of unknown classes, i.e., whose classes did not have any example during the training stage, need to be properly handled during testing. This specific setup is referred to in the literature as open-set recognition. Open-set problems are harder as they might be ill-sampled, not sampled at all, or even undefined. Differently from existing literature, here we aim at solving open-set recognition problems combining different classifiers and features while, at the same time, taking care of unknown classes. Researchers have greatly benefited from combining different methods in order to achieve more robust and reliable classifiers in daring recognition conditions, but those solutions have often focused on closed-set setups. In this paper, we propose the integration of a newly designed open-set graph-based optimum-path forest (OSOPF) classifier with genetic programming (GP) and majority voting fusion techniques. While OSOPF takes care of learning decision boundaries more resilient to unknown classes and outliers, GP combines different problem features to discover appropriate similarity functions and allows a more robust classification through early fusion. Finally, the majority-voting approach combines different classification evidence from different classifier outcomes and features through late-fusion techniques. Performed experiments show the proposed data-fusion approaches yield effective results for open-set recognition problems, significantly outperforming existing counterparts in the literature and paving the way for investigations in this field.
Scene text detection has become an important field in the computer vision area due to the increasing number of applications. This is a very challenging problem as textual elements are commonly found in “noisy” and complex natural scenes. Another issue refers to the presence of texts encoded into different languages within the same image. State-of-the-art solutions rely on the use of deep neural network approaches or even ensembles of them. However, such solutions are associated with “heavy” models, which are computationally expensive in terms of memory and storage footprints, which hampers their use in real-time mobile applications. In this work, we introduce Pelee-Text++, a lightweight neural network architecture for multi-lingual multi-oriented scene text detection, especially tailored to running on devices with computational restrictions. Additionally, to the best of our knowledge, this is the first work to evaluate the performance of text detection methods in commercial smartphones. Over this scenario, Pelee-Text++ processes 2.94 frames per second and it is the only evaluated approach that did not cause memory issues on smartphones, even using an input image of 1024×1024 pixels. Our proposal achieves a promising trade-off between efficiency and effectiveness, with a model size of 27 Megabytes and F-measure of 91.20%, 85.78%, 81.72%, 80.30%, 82.53% and 66.51% on ICDAR 2011, ICDAR 2013, ICDAR 2015, MSRA-TD500, ReCTS 2019 and Multi-lingual 2019 datasets, respectively.
Hundreds of text detection methods have been proposed, motivated by their widespread use in several applications. Despite the huge progress in the area, which includes even the use of sophisticated learning schemes, ad-hoc post-processing procedures are often employed to improve the text detection rate, by removing both false positives and negatives. Another issue refers to the lack of the use of the complementary views provided by different text detection methods. This paper aims to fill these gaps. We propose the use of a soft computing framework, based on genetic programming (GP), to guide the definition of suitable post-processing procedures through the combination of basic operators, which may be applied to improve detection results provided by multiple methods at the same time. Performed experiments in the widely used ICDAR 2011, ICDAR 2013, and ICDAR 2015 datasets demonstrate that our GP-based approach leads to F1 effectiveness gains up to 5.1 percentage points, when compared to several baselines.