Matching Items (2)
Filtering by
- All Subjects: Image Classification
- Creators: Chandakkar, Parag
- Creators: Watson, Matthew
Description
Uninformed people frequently kill snakes without knowing whether they are venomous or harmless, fearing for their safety. To prevent unnecessary killings and to encourage people to be safe around venomous snakes, a proper identification is important. This work seeks to preserve wild native Arizona snakes and promote a general interest in them by using a bag of features approach for classifying native Arizona snakes in images as venomous or non-venomous. The image category classifier was implemented in MATLAB and trained on a set of 245 images of native Arizona snakes (171 non-venomous, 74 venomous). To test this approach, 10-fold cross-validation was performed and the average accuracy was 0.7772. While this approach is functional, the results could be improved, ideally with a higher average accuracy, in order to be reliable. In false positives, the features may have been associated with the color or pattern, which is similar between venomous and non-venomous snakes due to mimicry. Polymorphic traits, color morphs, variation, and juveniles that may exhibit different colors can cause false negatives and misclassification. Future work involves pre-training image processing such as improving the brightness and contrast or converting to grayscale, interactively specifying or generating regions of interest for feature detection, and targeting reducing the false negative rate and improve the true positive rate. Further study is needed with a larger and balanced image set to evaluate its performance. This work may potentially serve as a tool for herpetologists to assist in their field research and to classify large image sets.
ContributorsIp, Melissa A (Author) / Li, Baoxin (Thesis director) / Chandakkar, Parag (Committee member) / Computer Science and Engineering Program (Contributor) / Barrett, The Honors College (Contributor)
Created2017-05
Description
In image classification tasks, images are often corrupted by spatial transformationslike translations and rotations. In this work, I utilize an existing method that uses
the Fourier series expansion to generate a rotation and translation invariant representation of closed contours found in sketches, aiming to attenuate the effects of distribution shift caused by the aforementioned transformations. I use this technique to
transform input images into one of two different invariant representations, a Fourier
series representation and a corrected raster image representation, prior to passing
them to a neural network for classification. The architectures used include convolutional neutral networks (CNNs), multi-layer perceptrons (MLPs), and graph neural
networks (GNNs). I compare the performance of this method to using data augmentation during training, the standard approach for addressing distribution shift, to see
which strategy yields the best performance when evaluated against a test set with
rotations and translations applied. I include experiments where the augmentations
applied during training both do and do not accurately reflect the transformations encountered at test time. Additionally, I investigate the robustness of both approaches
to high-frequency noise. In each experiment, I also compare training efficiency across
models. I conduct experiments on three data sets, the MNIST handwritten digit
dataset, a custom dataset (QD-3) consisting of three classes of geometric figures from
the Quick, Draw! hand-drawn sketch dataset, and another custom dataset (QD-345)
featuring sketches from all 345 classes found in Quick, Draw!. On the smaller problem space of MNIST and QD-3, the networks utilizing the Fourier-based technique to
attenuate distribution shift perform competitively with the standard data augmentation strategy. On the more complex problem space of QD-345, the networks using the
Fourier technique do not achieve the same test performance as correctly-applied data
augmentation. However, they still outperform instances where train-time augmentations mis-predict test-time transformations, and outperform a naive baseline model
where no strategy is used to attenuate distribution shift. Overall, this work provides
evidence that strategies which attempt to directly mitigate distribution shift, rather
than simply increasing the diversity of the training data, can be successful when
certain conditions hold.
ContributorsWatson, Matthew (Author) / Yang, Yezhou YY (Thesis advisor) / Kerner, Hannah HK (Committee member) / Yang, Yingzhen YY (Committee member) / Arizona State University (Publisher)
Created2023