Binary halftone image resolution increasing by decision tree learning.

IEEE Trans Image Process

Departamento de Engenharia de Sistemas Eletrônicos, Escola Politécnica, Universidade de São Paulo, 05508-900, São Paulo, Brazil.

Published: August 2004

This paper presents a new, accurate, and efficient technique to increase the spatial resolution of binary halftone images. It makes use of a machine learning process to automatically design a zoom operator starting from pairs of input-output sample images. To accurately zoom a halftone image, a large window and large sample images are required. Unfortunately, in this case, the execution time required by most of the previous techniques may be prohibitive. The new solution overcomes this difficulty by using decision tree (DT) learning. Original DT learning is modified to obtain a more efficient technique (WZDT learning). It is useful to know, a priori, sample complexity (the number of training samples needed to obtain, with probability 1 - delta, an operator with accuracy epsilon): we use the probably approximately correct (PAC) learning theory to compute the sample complexity. Since the PAC theory usually yields an overestimated sample complexity, statistical estimation is used to evaluate, a posteriori, a tight error bound. Statistical estimation is also used to choose an appropriate window and to show that DT learning has good inductive bias. The new technique is more accurate than a zooming method based on simple inverse halftoning techniques. The quality of the proposed solution is very close to the theoretical optimal obtainable quality for a neighborhood-based zooming process using the Hamming distance to quantify the error.

Download full-text PDF

Source
http://dx.doi.org/10.1109/tip.2004.828424DOI Listing

Publication Analysis

Top Keywords

sample complexity
12
binary halftone
8
halftone image
8
decision tree
8
tree learning
8
efficient technique
8
sample images
8
statistical estimation
8
learning
7
sample
5

Similar Publications

Youth's social status (popularity and likability) relates with social status goals as well as bullying and prosocial behaviors within the context of classroom norms for bullying and prosocial behaviors, but less clear is how each of these factors interrelates with each other. The current study empirically analyses the concurrent relationships among social status goals, bullying and prosocial behaviors, and classroom norms with social status. Participants were a nationally representative sample of 6,421 Slovenian early adolescents (50% females; M = 13 years; SD = 6 months).

View Article and Find Full Text PDF

Purpose: Few studies have examined disparities in-and social determinants of-contraception use among rural adolescents despite evidence of higher teen birth rates and greater STI risk in rural communities. Guided by a social determinants of health (SDoH) framework, this cross-sectional study aimed to address these gaps.

Methods: Data come from the 2018 Healthy Youth Survey, including N = 3757 sexually active, rural-based adolescents.

View Article and Find Full Text PDF

Digital PCR (dPCR) has transformed nucleic acid diagnostics by enabling the absolute quantification of rare mutations and target sequences. However, traditional dPCR detection methods, such as those involving flow cytometry and fluorescence imaging, may face challenges due to high costs, complexity, limited accuracy, and slow processing speeds. In this study, SAM-dPCR is introduced, a training-free open-source bioanalysis paradigm that offers swift and precise absolute quantification of biological samples.

View Article and Find Full Text PDF

This retrospective cohort study aimed to define the optimal Regions of Homozygosity (ROH) size cut-offs for prediction of morbidity, based on 13 483 Chromosomal Microarray Analyses (CMA). Receiver operating characteristic (ROC) curves were generated, and area under the curve (AUC) was used to assess the predictive capability of total ROH percentage (TRPS), ROH number and ROH segment size in distinguishing between healthy (n=6,196) and affected (n=6,839) cohorts. The metrics were examined for telomeric and interstitial segments, distinct TRPS categories, and across different ancestral origins.

View Article and Find Full Text PDF

Highly Efficient Analysis on Biomass Carbohydrate Mixtures by DREAMTIME NMR Spectroscopy.

Anal Chem

December 2024

Department of Electronic Science, Fujian Provincial Key Laboratory of Plasma and Magnetic Resonance, State Key Laboratory of Physical Chemistry of Solid Surfaces, Xiamen University, Siming South Road 422, Xiamen 361005, China.

Proton (H) NMR spectroscopy presents a powerful tool for biomass mixture studies by revealing the involved chemical compounds with identified ingredients and molecular structures. However, conventional H NMR generally suffers from spectral congestion when measuring biomass mixtures, particularly biomass carbohydrate samples, that contain various physically and chemically similar compounds. In this study, a targeted detection NMR approach, DREAMTIME, is exploited for studying biomass carbohydrate mixtures by spectroscopically targeting the desired compounds in separate 1D NMR spectra.

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!