SEGMENTACIÓN DE IMÁGENES DE COLOR EMPLEANDO EL ESPACIO DE ESCALA GAUSSIANO
Bibliographic record
Abstract
RESUMENLa visión por computador trata con el problema de encontrar interpretaciones o descripciones significativas a partir de datos visuales y se pueden pensar tres preguntas que conduzcan a la interpretación significativa de los mismos. ¿Cuál es la información relevante de la imagen? ¿Cómo debe extraerse la información relevante de los datos censados? ¿Qué medidas o características pueden obtenerse de la información extraída? Este trabajo pretende responder a la segunda pregunta, así como de identificar desde la imagen qué objetos están en el mundo y donde están en él. Se recurre a la representación en el espacio de escala para el análisis de los datos en diferentes niveles de la imagen y se propone una metodología de segmentación basada en la relación de cada uno de los píxeles con su vecindario.Los espacios de escala son reducciones sucesivas de características de la imagen que permiten identificar las propiedades más significativas de la misma, aplicando un filtro Gaussiano cuyos parámetros son variados a medida que la escala aumenta. Para las pruebas se emplearon imágenes de café y los resultados muestran regiones más completas con respecto a las técnicas de segmentación de crecimiento de regiones y SCT debido a la influencia del filtrado sucesivo. Este trabajo se desarrolló con apoyo del proyecto de investigación MODELADO DE SUPERFICIES DE FORMA LIBRE.PALABRAS CLAVE: Segmentación de Imágenes, Espacios de Escala, Filtro Gaussiano. ABSTRACT Computer vision deals with the problem of finding interpretations or significant descriptions from visual data. Three questions that lead to the significant interpretation of such data should be considered. What is the relevant information in the image? How can the relevant information be extracted from the data? What measures or characteristics can be obtained from the extracted information? This work tries to respond to the second question, as well as to identify what objects are in the image and where they are located.Scale space representation can be used to analyze the data from the image in different levels. In this work, a segmentation methodology based on the relation of each one of the pixels in the image with its neighbors is applied. Scale spaces are successive reductions of characteristics of the image that allow identification of its most significant properties. This is achieved by applying a Gaussian filter whose parameters are varied as the scale increases. Images of coffee plants were used for the tests and the results show more complete regions with respect to the techniques of segmentation of growth of regions and SCT. KEYWORDS: Segmentation of Images, Scale Space, Gaussian Filter.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.004 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".