Evaluating Machine Learning Approaches for ASCII Art Generation

• URL: http://arxiv.org/abs/2503.14375v1
• Date: Tue, 18 Mar 2025 16:07:29 GMT
• Title: Evaluating Machine Learning Approaches for ASCII Art Generation
• Abstract summary: This paper explores the application of modern machine learning methods to generate structured ASCII art.<n>We focus on three key criteria: fidelity, character classification accuracy, and output quality.<n>Our results show that complex neural network architectures often fall short in producing high-quality ASCII art.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Generating structured ASCII art using computational techniques demands a careful interplay between aesthetic representation and computational precision, requiring models that can effectively translate visual information into symbolic text characters. Although Convolutional Neural Networks (CNNs) have shown promise in this domain, the comparative performance of deep learning architectures and classical machine learning methods remains unexplored. This paper explores the application of contemporary ML and DL methods to generate structured ASCII art, focusing on three key criteria: fidelity, character classification accuracy, and output quality. We investigate deep learning architectures, including Multilayer Perceptrons (MLPs), ResNet, and MobileNetV2, alongside classical approaches such as Random Forests, Support Vector Machines (SVMs) and k-Nearest Neighbors (k-NN), trained on an augmented synthetic dataset of ASCII characters. Our results show that complex neural network architectures often fall short in producing high-quality ASCII art, whereas classical machine learning classifiers, despite their simplicity, achieve performance similar to CNNs. Our findings highlight the strength of classical methods in bridging model simplicity with output quality, offering new insights into ASCII art synthesis and machine learning on image data with low dimensionality.

Related papers

• Unlocking the Latent Canvas: Eliciting and Benchmarking Symbolic Visual Expression in LLMs [24.67518539705944]
  Current approaches predominantly treat visual generation as an external process, relying on pixel rendering or code execution.<n>In this work, we unlock this potential through ASCII art, a compact, efficient, and text-native visual format.<n>We introduce SVE-ASCII, a unified framework designed to elicit and benchmark Visual Expression directly within the pure text space.
  arXiv  Detail & Related papers  (2026-03-15T17:38:10Z)
• ASCIIBench: Evaluating Language-Model-Based Understanding of Visually-Oriented Text [3.7458289725370855]
  We introduce ASCIIBench, a novel benchmark for evaluating the generation and classification of ASCII-text images.<n>Our analysis shows that cosine similarity over CLIP embeddings fails to separate most ASCII categories.<n>These findings position ASCII art as a stress test for multimodal representations.
  arXiv  Detail & Related papers  (2025-12-02T20:55:42Z)
• Multimodal Structure-Aware Quantum Data Processing [0.8287206589886879]
  We develop a framework for structure-aware data processing with multimodal+image data.<n>"structure" refers to syntactic and grammatical relationships in language, as well as the hierarchical organization of visual elements in images.<n>When tested on a main stream image classification task, our best model showed a par performance with the state of the art classical models.
  arXiv  Detail & Related papers  (2024-11-06T20:11:19Z)
• Visual Perception in Text Strings [24.60102607739684]
  In this work, we select ASCII art as a representative artifact, where the lines and brightness used to depict each concept are rendered by characters. We benchmark model performance on this task by constructing an evaluation dataset and also collect a training set to elicit the models' visual perception ability. Results reveal that although humans can achieve nearly 100% accuracy, the state-of-the-art LLMs and MLLMs lag far behind.
  arXiv  Detail & Related papers  (2024-10-02T16:46:01Z)
• Adinkra Symbol Recognition using Classical Machine Learning and Deep Learning [0.0]
  We build a CNN model for classification and recognition using six convolutional layers, three fully connected layers, and optional dropout regularization. We assess the model's performance by measuring its accuracy and convergence rate. We hope this application inspires ideas on the various uses of AI in organizing our traditional and modern lives.
  arXiv  Detail & Related papers  (2023-11-27T11:26:41Z)
• Homological Convolutional Neural Networks [4.615338063719135]
  We propose a novel deep learning architecture that exploits the data structural organization through topologically constrained network representations. We test our model on 18 benchmark datasets against 5 classic machine learning and 3 deep learning models.
  arXiv  Detail & Related papers  (2023-08-26T08:48:51Z)
• Revisiting Classifier: Transferring Vision-Language Models for Video Recognition [102.93524173258487]
  Transferring knowledge from task-agnostic pre-trained deep models for downstream tasks is an important topic in computer vision research. In this study, we focus on transferring knowledge for video classification tasks. We utilize the well-pretrained language model to generate good semantic target for efficient transferring learning.
  arXiv  Detail & Related papers  (2022-07-04T10:00:47Z)
• GIT: A Generative Image-to-text Transformer for Vision and Language [138.91581326369837]
  We train a Generative Image-to-text Transformer, GIT, to unify vision-language tasks such as image/video captioning and question answering. Our model surpasses the human performance for the first time on TextCaps (138.2 vs. 125.5 in CIDEr)
  arXiv  Detail & Related papers  (2022-05-27T17:03:38Z)
• Adaptive Convolutional Dictionary Network for CT Metal Artifact Reduction [62.691996239590125]
  We propose an adaptive convolutional dictionary network (ACDNet) for metal artifact reduction. Our ACDNet can automatically learn the prior for artifact-free CT images via training data and adaptively adjust the representation kernels for each input CT image. Our method inherits the clear interpretability of model-based methods and maintains the powerful representation ability of learning-based methods.
  arXiv  Detail & Related papers  (2022-05-16T06:49:36Z)
• Comparison Analysis of Traditional Machine Learning and Deep Learning Techniques for Data and Image Classification [62.997667081978825]
  The purpose of the study is to analyse and compare the most common machine learning and deep learning techniques used for computer vision 2D object classification tasks. Firstly, we will present the theoretical background of the Bag of Visual words model and Deep Convolutional Neural Networks (DCNN) Secondly, we will implement a Bag of Visual Words model, the VGG16 CNN Architecture.
  arXiv  Detail & Related papers  (2022-04-11T11:34:43Z)
• Image Classification with Classic and Deep Learning Techniques [0.0]
  We implement an image classifier using both classic computer vision and deep learning techniques. We evaluate each of the cases in terms of accuracy and loss, and we obtain results that vary between 0.6 and 0.96 depending on the model and configuration used.
  arXiv  Detail & Related papers  (2021-05-11T09:32:38Z)
• Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision [57.031588264841]
  We leverage a noisy dataset of over one billion image alt-text pairs, obtained without expensive filtering or post-processing steps. A simple dual-encoder architecture learns to align visual and language representations of the image and text pairs using a contrastive loss. We show that the scale of our corpus can make up for its noise and leads to state-of-the-art representations even with such a simple learning scheme.
  arXiv  Detail & Related papers  (2021-02-11T10:08:12Z)
• Synbols: Probing Learning Algorithms with Synthetic Datasets [112.45883250213272]
  Synbols is a tool for rapidly generating new datasets with a rich composition of latent features rendered in low resolution images. Our tool's high-level interface provides a language for rapidly generating new distributions on the latent features. To showcase the versatility of Synbols, we use it to dissect the limitations and flaws in standard learning algorithms in various learning setups.
  arXiv  Detail & Related papers  (2020-09-14T13:03:27Z)
• Improved Code Summarization via a Graph Neural Network [96.03715569092523]
  In general, source code summarization techniques use the source code as input and outputs a natural language description. We present an approach that uses a graph-based neural architecture that better matches the default structure of the AST to generate these summaries.
  arXiv  Detail & Related papers  (2020-04-06T17:36:42Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.