Pill-ID: Matching and retrieval of drug pill images

Lee, Young-Beom; Park, Unsang; Jain, Anil K.; Lee, Seong–Whan

doi:10.1016/j.patrec.2011.08.022

Cited by 47 publications

(30 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…We evaluate the potential use of this metric for a retrieval paradigm. In order to assess its usefulness we use a slightly modified version of the recall metric, which is widely accepted as a performance measure in such retrieval paradigms [2,14]. The recall metric, normally calculated as…”

Section: Application To Query Refinementmentioning

confidence: 99%

“…The improvement in modified recall demonstrates the value of granularity in a database retrieval context. The initial candidate ranking can be defined by any number of established features used in databases retrieval tasks such as: shape [15,16], colour [17,4], logo [4,2,6], diameter mass and thickness [18,5], or chemical profile [18,19,5,7,1]. After normalizing the candidate score as returned by any one of these metrics to a value between 0 and 1 we multiply these scores by the weighted and normalized likelihood ratio of a match between two granularity profiles.…”

Section: Application To Query Refinementmentioning

confidence: 99%

“…Illicit tablets, produced in clandestine laboratories, often feature distinctive physical characteristics [1,2]. Whether these characteristics are intended to identify a particular product to illicit market consumers or to indicate particular dosages between multiple production batches [3], they are of great value to profiling efforts made in a forensic context.…”

Section: Introductionmentioning

confidence: 99%

“…In forensic intelligence, potential links between seizures can emerge based on physical features and then be more closely examined using chemical analysis. Research into the applicability of physical features for XTC tablet matching has demonstrated useful results from an evidential perspective [4,5,1], as well as for intelligence driven applications [2,6]. These applications often make use of physical features such as the shape, colour, mass, diameter, thickness and some description of the logo.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Surface granularity as a discriminating feature of illicit tablets

Lopatka

2011

Forensic Science International

View full text Add to dashboard Cite

Section: Application To Query Refinementmentioning

confidence: 99%

Section: Application To Query Refinementmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Surface granularity as a discriminating feature of illicit tablets

Lopatka

2011

Forensic Science International

View full text Add to dashboard Cite

“…The closest match of the gallery identifies the query image. Later [7] a refined journal version of the same work, reveals a different strategy. Multi-scale Local Binary Pattern (MLBP) and Scale Invariant Feature Transform (SIFT) are used to find the keypoints mapping pill imprinting.…”

Section: Introductionmentioning

confidence: 99%

HelpmePills: A Mobile Pill Recognition Tool for Elderly Persons

Cunha

Adão

Trigueiros

2014

Procedia Technology

View full text Add to dashboard Cite

Aging is a natural process typically characterized by loss of capabilities such as vision or memory. These transformations interfere with quotidian tasks performance sometimes leading to dangerous situations for senior adults. One of the most relevant is related with the wrong ingestion of medication or even forgetfulness. This kind of mistakes represents a real threat to elder's health and life. Furthermore, the existing technological solutions concerned with this problematic, are designed for professionals or general public disregarding elderly needs in particular. Thus, in order to overcome this lack of support, it will be presented an image processing tool, which represents the first steps for a larger toolset adapted for elderly persons, under construction. The procedures followed by this proposal include image acquisition and pill characterization based on its shape, dimensions and colors. The system uses these features in the learning step to describe and store pills information on local database. Later, in the recognition step, the same features are determined and compared against database in order to provide the user with relevant informations related with the pill under recognition.

show abstract

Pill identification: comparing the identification accuracy and error rates of Internet search engines and standard pill identification applications by entering visual characteristics

Shenker

Turner

Brandspiegel

2018

Pharmacy Practice and Res

View full text Add to dashboard Cite

Background: Proper identification of medications is important for patient safety. Many pill identification applications are available to help identify tablets/capsules but their accuracy varies. Internet search engines could be an alternative for identification. Aim: The hypothesis was that Internet search engines would perform as well as or better than pill identification applications in determining the name and dosage of medications. Methods: A set of images of 451 pills was prepared. Visual characteristics were entered into two Internet search engines and three pill identification applications. Head to head comparisons of correct identifications were made using McNemar's test. Results: No statistically significant difference was found in correct identifications between Google (93.6%) and Drugs.com (94.0%). Both Google and Drugs.com performed better than Bing (91.4%) at the p < 0.05 level. Drugs.com, Google and Bing all performed better than Pillbox (68.3%) and Epocrates (54.1%) at the p < 0.0001 level. Conclusion: Internet search engines perform well in pill identification and better than some dedicated pill identification applications.

show abstract

Pill-ID: Matching and retrieval of drug pill images

Cited by 47 publications

References 15 publications

Surface granularity as a discriminating feature of illicit tablets

Surface granularity as a discriminating feature of illicit tablets

HelpmePills: A Mobile Pill Recognition Tool for Elderly Persons

Pill identification: comparing the identification accuracy and error rates of Internet search engines and standard pill identification applications by entering visual characteristics

Contact Info

Product

Resources

About