Skip to content

Commit bd4988d

Browse files
agarnungagarnung
committed
Pestaña abous
1 parent 992a00d commit bd4988d

File tree

9 files changed

+63
-36
lines changed

9 files changed

+63
-36
lines changed

‎_data/other-skills.yml‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -11,7 +11,7 @@
1111
- name: Dev Tools
1212
percentage: 60
1313
color: success
14-
subtitle: Linux, Bash, Qt, OpenGL, GLSL, CUDA
14+
subtitle: Linux, Bash, Qt, GLSL, CUDA, OpenGL
1515

1616
- name: DevOps & Automation
1717
percentage: 30

‎_data/papers.yml‎

Lines changed: 6 additions & 14 deletions
Original file line numberDiff line numberDiff line change
@@ -1,15 +1,7 @@
1-
- title: "Physics Meets Pixels: PDE Models in Image Processing"
2-
date: 11 dic. 2024
3-
url: https://arxiv.org/abs/2412.11946
4-
publisher: arxiv (Cornell Tech)
5-
image: '/assets/publications_images/preprints/pixels.png'
1+
- title: "A Novel Approach to Speed Up Hampel Filter for Outlier Detection"
2+
date: 23 may 2025
3+
url: https://www.mdpi.com/1424-8220/25/11/3319
4+
publisher: Sensors (MDPI)
5+
image: '/assets/publications_images/hfv.png'
66
description: |
7-
Partial Differential Equations (PDEs) have long been recognized as powerful tools for image processing and analysis, providing a framework to model and exploit structural and geometric properties inherent in visual data. Over the years, numerous PDE-based models have been developed and refined, inspired by natural analogies between physical phenomena and image spaces. These methods have proven highly effective in a wide range of applications, including denoising, deblurring, sharpening, inpainting, feature extraction, and others. This work provides a theoretical and computational exploration of both fundamental and innovative PDE models applied to image processing, accompanied by extensive numerical experimentation and objective and subjective analysis. Building upon well-established techniques, we introduce novel physical-based PDE models specifically designed for various image processing tasks. These models incorporate mathematical principles and approaches that, to the best of our knowledge, have not been previously applied in this domain, showcasing their potential to address challenges beyond the capabilities of traditional and existing PDE methods. By formulating and solving these mathematical models, we demonstrate their effectiveness in advancing image processing tasks while retaining a rigorous connection to their theoretical underpinnings. This work seeks to bridge foundational concepts and cutting-edge innovations, contributing to the evolution of PDE methodologies in digital image processing and related interdisciplinary fields. <a href="https://github.com/agarnung/agarnung.github.io/tree/main/assets/publications_data/pdesinpdi_metrics_evaluation">Link to code</a>.
8-
9-
- title: "A Hybrid Frameworkfor Statistical Feature Selection and Image-Based Noise-Defect Detection"
10-
date: 11 dic. 2024
11-
url: https://www.arxiv.org/abs/2412.08800
12-
publisher: arxiv (Cornell Tech)
13-
image: '/assets/publications_images/preprints/hybrid.png'
14-
description: |
15-
In industrial imaging, accurately detecting and distinguishing surface defects from noise is critical and challenging, particularly in complex environments with noisy data. This paper presents a hybrid framework that integrates both statistical feature selection and classification techniques to improve defect detection accuracy while minimizing false positives. The motivation of the system is based on the generation of scalar scores that represent the likelihood that a region of interest (ROI) is classified as a defect or noise. We present around 55 distinguished features that are extracted from industrial images, which are then analyzed using statistical methods such as Fisher separation, chi-squared test, and variance analysis. These techniques identify the most discriminative features, focusing on maximizing the separation between true defects and noise. Fisher's criterion ensures robust, real-time performance for automated systems. This statistical framework opens up multiple avenues for application, functioning as a standalone assessment module or as an a posteriori enhancement to machine learning classifiers. The framework can be implemented as a black-box module that applies to existing classifiers, providing an adaptable layer of quality control and optimizing predictions by leveraging intuitive feature extraction strategies, emphasizing the rationale behind feature significance and the statistical rigor of feature selection. By integrating these methods with flexible machine learning applications, the proposed framework improves detection accuracy and reduces false positives and misclassifications, especially in complex, noisy environments.
7+
Outlier detection is a critical task in time series analysis, essential to maintaining data quality and allowing for accurate subsequent analysis. The Hampel filter, a decision filter that replaces outliers in a data window with the median, is widely used for outlier detection in time series due to its simplicity and effectiveness. While effective, its computational complexity, primarily due to the calculation of the Median Absolute Deviation (MAD), poses limitations for large-scale and real-time applications. This paper proposes a novel Hampel filter variant that replaces the MAD with an original estimator (mMAD) that retains statistical robustness but is computationally more efficient. This reduces the filter’s computational complexity from 𝑂(𝑁·𝑤log𝑤) to 𝑂(𝑁·𝑤), where N is the data length and w the window size. The proposed variant significantly lowers processing time and resource consumption, making it especially suitable for large-scale and real-time data processing while preserving robust outlier detection performance.

‎_data/preprints.yml‎

Lines changed: 15 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,15 @@
1+
- title: "Physics Meets Pixels: PDE Models in Image Processing"
2+
date: 11 dic. 2024
3+
url: https://arxiv.org/abs/2412.11946
4+
publisher: arxiv (Cornell Tech)
5+
image: '/assets/publications_images/preprints/pixels.png'
6+
description: |
7+
Partial Differential Equations (PDEs) have long been recognized as powerful tools for image processing and analysis, providing a framework to model and exploit structural and geometric properties inherent in visual data. Over the years, numerous PDE-based models have been developed and refined, inspired by natural analogies between physical phenomena and image spaces. These methods have proven highly effective in a wide range of applications, including denoising, deblurring, sharpening, inpainting, feature extraction, and others. This work provides a theoretical and computational exploration of both fundamental and innovative PDE models applied to image processing, accompanied by extensive numerical experimentation and objective and subjective analysis. Building upon well-established techniques, we introduce novel physical-based PDE models specifically designed for various image processing tasks. These models incorporate mathematical principles and approaches that, to the best of our knowledge, have not been previously applied in this domain, showcasing their potential to address challenges beyond the capabilities of traditional and existing PDE methods. By formulating and solving these mathematical models, we demonstrate their effectiveness in advancing image processing tasks while retaining a rigorous connection to their theoretical underpinnings. This work seeks to bridge foundational concepts and cutting-edge innovations, contributing to the evolution of PDE methodologies in digital image processing and related interdisciplinary fields. <a href="https://github.com/agarnung/agarnung.github.io/tree/main/assets/publications_data/pdesinpdi_metrics_evaluation">Link to code</a>.
8+
9+
- title: "A Hybrid Frameworkfor Statistical Feature Selection and Image-Based Noise-Defect Detection"
10+
date: 11 dic. 2024
11+
url: https://www.arxiv.org/abs/2412.08800
12+
publisher: arxiv (Cornell Tech)
13+
image: '/assets/publications_images/preprints/hybrid.png'
14+
description: |
15+
In industrial imaging, accurately detecting and distinguishing surface defects from noise is critical and challenging, particularly in complex environments with noisy data. This paper presents a hybrid framework that integrates both statistical feature selection and classification techniques to improve defect detection accuracy while minimizing false positives. The motivation of the system is based on the generation of scalar scores that represent the likelihood that a region of interest (ROI) is classified as a defect or noise. We present around 55 distinguished features that are extracted from industrial images, which are then analyzed using statistical methods such as Fisher separation, chi-squared test, and variance analysis. These techniques identify the most discriminative features, focusing on maximizing the separation between true defects and noise. Fisher's criterion ensures robust, real-time performance for automated systems. This statistical framework opens up multiple avenues for application, functioning as a standalone assessment module or as an a posteriori enhancement to machine learning classifiers. The framework can be implemented as a black-box module that applies to existing classifiers, providing an adaptable layer of quality control and optimizing predictions by leveraging intuitive feature extraction strategies, emphasizing the rationale behind feature significance and the statistical rigor of feature selection. By integrating these methods with flexible machine learning applications, the proposed framework improves detection accuracy and reduces false positives and misclassifications, especially in complex, noisy environments.

‎_data/programming-skills.yml‎

Lines changed: 6 additions & 6 deletions
Original file line numberDiff line numberDiff line change
@@ -1,4 +1,4 @@
1-
- name: C/C++
1+
- name: C/C++/C#
22
percentage: 70
33
color: danger
44
subtitle:
@@ -8,16 +8,16 @@
88
color: info
99
subtitle:
1010

11+
- name: Web development
12+
percentage: 20
13+
color: primary
14+
subtitle: HTML, (S)CSS, JavaScript, Jekyll, Flask, FastAPI, Vercel, Jekyll, Svelte, Astro
15+
1116
- name: Assembly (x86/64)
1217
percentage: 20
1318
color: secondary
1419
subtitle:
1520

16-
- name: Web development
17-
percentage: 20
18-
color: primary
19-
subtitle: HTML, (S)CSS, JavaScript, Jekyll, Flask, Svelte, Astro
20-
2121
- name: Databases
2222
percentage: 20
2323
color: dark

‎_data/publications.yml‎ renamed to ‎_data/works.yml‎

Lines changed: 0 additions & 8 deletions
Original file line numberDiff line numberDiff line change
@@ -1,11 +1,3 @@
1-
- title: "A Novel Approach to Speed Up Hampel Filter for Outlier Detection"
2-
date: 23 may 2025
3-
url: https://www.mdpi.com/1424-8220/25/11/3319
4-
publisher: Sensors (MDPI)
5-
image: '/assets/publications_images/hfv.png'
6-
description: |
7-
Outlier detection is a critical task in time series analysis, essential to maintaining data quality and allowing for accurate subsequent analysis. The Hampel filter, a decision filter that replaces outliers in a data window with the median, is widely used for outlier detection in time series due to its simplicity and effectiveness. While effective, its computational complexity, primarily due to the calculation of the Median Absolute Deviation (MAD), poses limitations for large-scale and real-time applications. This paper proposes a novel Hampel filter variant that replaces the MAD with an original estimator (mMAD) that retains statistical robustness but is computationally more efficient. This reduces the filter’s computational complexity from 𝑂(𝑁·𝑤log𝑤) to 𝑂(𝑁·𝑤), where N is the data length and w the window size. The proposed variant significantly lowers processing time and resource consumption, making it especially suitable for large-scale and real-time data processing while preserving robust outlier detection performance.
8-
91
- title: "Development of a system for the validation of industrial parts pose on conveyor belts with a focus on simulation and advanced experimentation (Master's Thesis)"
102
date: 15 feb. 2024
113
url: https://digibuo.uniovi.es/dspace/handle/10651/76231

‎_includes/about/papers.html‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -6,7 +6,7 @@
66
<h2>{{ item.title }}</h2>
77
<h6 class="date">{{ item.date }}</h6>
88
<div style="display: flex; align-items: center; gap: 10px;">
9-
<h6 class="url"><a target="_blank" href="{{ item.url }}">Link to preprint</a></h6>
9+
<h6 class="url"><a target="_blank" href="{{ item.url }}">Link to paper</a></h6>
1010
<h6 class="publisher">- {{ item.publisher }}</h6>
1111
</div>
1212
<strong>Abstract:</strong>

‎_includes/about/preprints.html‎

Lines changed: 19 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,19 @@
1+
<div class="col mt-4">
2+
<div class="timeline-body bg-themed">
3+
{% for item in site.data.preprints %}
4+
<div class="timeline-item">
5+
<div class="content">
6+
<h2>{{ item.title }}</h2>
7+
<h6 class="date">{{ item.date }}</h6>
8+
<div style="display: flex; align-items: center; gap: 10px;">
9+
<h6 class="url"><a target="_blank" href="{{ item.url }}">Link to preprint</a></h6>
10+
<h6 class="language">- {{ item.language }}</h6>
11+
</div>
12+
<strong>Description:</strong>
13+
<p style="text-align:justify; font-size:13px"><i>{{ item.description }}</i></p>
14+
<img src="{{ item.image }}" alt="" class="center">
15+
</div>
16+
</div>
17+
{% endfor %}
18+
</div>
19+
</div>

‎_includes/about/publications.html‎ renamed to ‎_includes/about/works.html‎

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -1,12 +1,12 @@
11
<div class="col mt-4">
22
<div class="timeline-body bg-themed">
3-
{% for item in site.data.publications %}
3+
{% for item in site.data.works %}
44
<div class="timeline-item">
55
<div class="content">
66
<h2>{{ item.title }}</h2>
77
<h6 class="date">{{ item.date }}</h6>
88
<div style="display: flex; align-items: center; gap: 10px;">
9-
<h6 class="url"><a target="_blank" href="{{ item.url }}">Link to PDF</a></h6>
9+
<h6 class="url"><a target="_blank" href="{{ item.url }}">Link to work</a></h6>
1010
<h6 class="language">- {{ item.language }}</h6>
1111
</div>
1212
<strong>Description:</strong>

‎pages/publications.md‎

Lines changed: 13 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -5,24 +5,33 @@ permalink: /publications/
55
weight: 2
66
---
77

8-
# **Publications**
8+
# **Papers**
99

10+
Some journal publications during research time.
1011

1112
<div class="row">
12-
{% include about/publications.html %}
13+
{% include about/papers.html %}
1314
</div>
1415

1516
## **Preprints**
1617

1718
Eventually, I research a few exciting topics in image processing and computer vision.
1819

1920
<div class="row">
20-
{% include about/papers.html %}
21+
{% include about/preprints.html %}
22+
</div>
23+
24+
## **Works**
25+
26+
My academic finals projectss, published openly.
27+
28+
<div class="row">
29+
{% include about/works.html %}
2130
</div>
2231

2332
## **Other**
2433

25-
A few papers and some more informal, short-format essays.
34+
A few write-ups and more informal, short-format essays.
2635

2736
<div class="row">
2837
{% include about/other.html %}

0 commit comments

Comments
 (0)