Dataset Information

Reading 1D Barcodes with Mobile Phones Using Deformable Templates.

ABSTRACT: Camera cellphones have become ubiquitous, thus opening a plethora of opportunities for mobile vision applications. For instance, they can enable users to access reviews or price comparisons for a product from a picture of its barcode while still in the store. Barcode reading needs to be robust to challenging conditions such as blur, noise, low resolution, or low-quality camera lenses, all of which are extremely common. Surprisingly, even state-of-the-art barcode reading algorithms fail when some of these factors come into play. One reason resides in the early commitment strategy that virtually all existing algorithms adopt: The image is first binarized and then only the binary data are processed. We propose a new approach to barcode decoding that bypasses binarization. Our technique relies on deformable templates and exploits all of the gray-level information of each pixel. Due to our parameterization of these templates, we can efficiently perform maximum likelihood estimation independently on each digit and enforce spatial coherence in a subsequent step. We show by way of experiments on challenging UPC-A barcode images from five different databases that our approach outperforms competing algorithms. Implemented on a Nokia N95 phone, our algorithm can localize and decode a barcode on a VGA image (640 × 480, JPEG compressed) in an average time of 400-500 ms.

SUBMITTER: Gallo O

PROVIDER: S-EPMC3190667 | biostudies-literature | 2011 Sep

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Reading 1D Barcodes with Mobile Phones Using Deformable Templates.

Gallo Orazio O Manduchi Roberto R

IEEE transactions on pattern analysis and machine intelligence 20101223 9

Camera cellphones have become ubiquitous, thus opening a plethora of opportunities for mobile vision applications. For instance, they can enable users to access reviews or price comparisons for a product from a picture of its barcode while still in the store. Barcode reading needs to be robust to challenging conditions such as blur, noise, low resolution, or low-quality camera lenses, all of which are extremely common. Surprisingly, even state-of-the-art barcode reading algorithms fail when some ...[more]

PMID: 21173448

Similar Datasets

Project description:BackgroundMobile phones offer new opportunities to efficiently and interactively collect real-time data from patients with acute illnesses, such as urinary tract infections (UTIs). One of the main benefits of using mobile data collection methods is automated data upload, which can reduce the chance of data loss, an issue when using other data collection methods such as paper-based surveys.ObjectiveThe aim was to explore differences in collecting data from patients with UTI using text messaging, a mobile phone app (UTI diary), and an online survey. This paper provides lessons learned from integrating mobile data collection into a randomized controlled trial.MethodsParticipants included UTI patients consulting in general practices that were participating in the Supporting the Improvement and Management of UTI (SIMPle) study. SIMPle was designed to improve prescribing antimicrobial therapies for UTI in the community. Patients were invited to reply to questions regarding their UTI either via a prospective text message survey, a mobile phone app (UTI diary), or a retrospective online survey. Data were collected from 329 patients who opted in to the text message survey, 71 UTI patients through the mobile phone UTI symptom diary app, and 91 online survey participants.ResultsThe age profile of UTI diary app users was younger than that of the text message and online survey users. The largest dropout for both the text message survey respondents and UTI diary app users was after the initial opt-in message; once the participants completed question 1 of the text message survey or day 2 in the UTI diary app, they were more likely to respond to the remaining questions/days.ConclusionsThis feasibility study highlights the potential of using mobile data collection methods to capture patient data. As well as improving the efficiency of data collection, these novel approaches highlight the advantage of collecting data in real time across multiple time points. There was little variation in the number of patients responding between text message survey, UTI diary, and online survey, but more patients participated in the text message survey than the UTI diary app. The choice between designing a text message survey or UTI diary app will depend on the age profile of patients and the type of information the researchers' desire.Trial registrationClinicalTrials.gov NCT01913860; https://clinicaltrials.gov/ct2/show/NCT01913860 (Archived by WebCite at http://www.webcitation.org/6pfgCztgT).

Project description:The stepped-care approach, where people with early symptoms of depression are stepped up from low-intensity interventions to higher-level interventions as needed, has the potential to assist many people with mild depressive symptoms. Self-monitoring techniques assist people to understand their mental health symptoms by increasing their emotional self-awareness (ESA) and can be easily distributed on mobile phones at low cost. Increasing ESA is an important first step in psychotherapy and has the potential to intervene before mild depressive symptoms progress to major depressive disorder. In this secondary analysis we examined a mobile phone self-monitoring tool used by young people experiencing mild or more depressive symptoms to investigate the relationships between self-monitoring, ESA, and depression.We tested two main hypotheses: (1) people who monitored their mood, stress, and coping strategies would have increased ESA from pretest to 6-week follow-up compared with an attention comparison group, and (2) an increase in ESA would predict a decrease in depressive symptoms.We recruited patients aged 14 to 24 years from rural and metropolitan general practices. Eligible participants were identified as having mild or more mental health concerns by their general practitioner. Participants were randomly assigned to either the intervention group (where mood, stress, and daily activities were monitored) or the attention comparison group (where only daily activities were monitored), and both groups self-monitored for 2 to 4 weeks. Randomization was carried out electronically via random seed generation, by an in-house computer programmer; therefore, general practitioners, participants, and researchers were blinded to group allocation at randomization. Participants completed pretest, posttest, and 6-week follow-up measures of the Depression Anxiety Stress Scale and the ESA Scale. We estimated a parallel process latent growth curve model (LGCM) using Mplus to test the indirect effect of the intervention on depressive symptoms via the mediator ESA, and calculated 95% bias-corrected bootstrapping confidence intervals (CIs).Of the 163 participants assessed for eligibility, 118 were randomly assigned and 114 were included in analyses (68 in the intervention group and 46 in the comparison group). A parallel process LGCM estimated the indirect effect of the intervention on depressive symptoms via ESA and was shown to be statistically significant based on the 95% bias-corrected bootstrapping CIs not containing zero (-6.366 to -0.029). The proportion of the maximum possible indirect effect estimated was ?(2 )=.54 (95% CI .426-.640).This study supported the hypothesis that self-monitoring increases ESA, which in turn decreases depressive symptoms for young people with mild or more depressive symptoms. Mobile phone self-monitoring programs are ideally suited to first-step intervention programs for depression in the stepped-care approach, particularly when ESA is targeted as a mediating factor.ClinicalTrials.gov NCT00794222; http://clinicaltrials.gov/ct2/show/NCT00794222 (Archived by WebCite at http://www.webcitation.org/65lldW34k).

Dataset Information

Reading 1D Barcodes with Mobile Phones Using Deformable Templates.

Publications

Reading 1D Barcodes with Mobile Phones Using Deformable Templates.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets