Rozdziały

Stały URI dla kolekcjihttp://hdl.handle.net/11652/4775

Przeglądaj

Filtry

20232

Ustawienia

Tematsearch.filters.applied.operator.equals: search.filters.subject.convolutional neural networks

collection.search.results.head

Teraz wyświetlane 1 - 2 z 2
  • Pozycja
    Increasing Skin Lesions Classification Rates using Convolutional Neural Networks with Invariant Dataset Augmentation and the Three-Point Checklist of Dermoscopy
    (Wydawnictwo Politechniki Łódzkiej, 2023) Milczarski, Piotr; Borowski, Norbert; Beczkowski, Michał
    In the paper, we show how to tackle the problem of lack of the rotation invariance in CNN networks using the authors’ Invariant Dataset Augmentation (IDA) method. The IDA method allows to increase the classification rates taking into account as an example the classification of the skin lesions using a small image set. In order to solve the problem of the lack of rotation invariance, IDA method was used and the dataset was increased in an eightfold and invariant way. In the research, we applied the IDA methods and compared the results of VGG19, XN and Inception-ResNetv2 CNN networks in three skin lesions features classification defined by wellknown dermoscopic criterions e.g. the Three-Point Checklist of Dermoscopy or the Seven-Point Checklist. Due to Invariant Dataset Augmentation, the classification rate parameters like true positive rate by almost 20%, false positive rate as well as the F1 score and Matthews correlation coefficient have been significantly increased opposite to type II error that has significantly decreased. In the paper, the confusion matrix parameters result in: 98-100% accuracy, 98-100% true positive rate, 0.0-2.3% false positive rate, tests F1=0.95 and MCC=0.95. That general approach can provide higher results while using CNN networks in other applications.
  • Pozycja
    Pedestrian Detection with High-resolution Event Camera
    (Wydawnictwo Politechniki Łódzkiej, 2023) Wzorek, Piotr; Kryjak, Tomasz
    Despite the dynamic development of computer vision algorithms, the implementation of perception and control systems for autonomous vehicles such as drones and self-driving cars still poses many challenges. A video stream captured by traditional cameras is often prone to problems such as motion blur or degraded image quality caused due to challenging lighting conditions. In addition, the frame rate – typically 30 or 60 frames per second – can be a limiting factor in certain scenarios. Event cameras (DVS – Dynamic Vision Sensor) are a potentially interesting technology to address the above mentioned problems. In this paper, we compare two methods of processing event data by means of deep learning for the task of pedestrian detection. We used a representation in the form of video frames, convolutional neural networks and asynchronous sparse convolutional neural networks. The results obtained illustrate the potential of event cameras and allow the evaluation of the effectiveness and efficiency of the methods used for high-resolution (1280 x 720 pixels) footage.