Pattern Recognition in Dried Milk Droplets Using Lacunarity and Deep Learning

This study introduces a novel method for classifying whole and lactose-free milk and the detection of water adulteration through analyzing dried droplets. The key innovation is the addition of NaCl, which modulates crystallization to enhance structural differentiation and facilitate the classificati...

Full description

Saved in:
Bibliographic Details
Main Authors: Josías N. Molina-Courtois, Yaquelin Josefa Aguilar Morales, Luis Escalante-Zarate, Mario Castelán, Yojana J. P. Carreón, Jorge González-Gutiérrez
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/10/5676
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850257458042241024
author Josías N. Molina-Courtois
Yaquelin Josefa Aguilar Morales
Luis Escalante-Zarate
Mario Castelán
Yojana J. P. Carreón
Jorge González-Gutiérrez
author_facet Josías N. Molina-Courtois
Yaquelin Josefa Aguilar Morales
Luis Escalante-Zarate
Mario Castelán
Yojana J. P. Carreón
Jorge González-Gutiérrez
author_sort Josías N. Molina-Courtois
collection DOAJ
description This study introduces a novel method for classifying whole and lactose-free milk and the detection of water adulteration through analyzing dried droplets. The key innovation is the addition of NaCl, which modulates crystallization to enhance structural differentiation and facilitate the classification of milk types and detection of adulteration. Dried droplets of milk containing NaCl concentrations of <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>0</mn><mo>%</mo></mrow></semantics></math></inline-formula>, <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>2</mn><mo>%</mo></mrow></semantics></math></inline-formula>, and <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>4</mn><mo>%</mo></mrow></semantics></math></inline-formula> were analyzed, revealing distinct morphologies, including amorphous, cross-shaped, and dendritic crystals. These structures were quantitatively characterized using lacunarity to assess their discriminatory power. Two classification approaches were evaluated: one based on lacunarity analysis alone and another incorporating deep learning. Both methods yielded high classification accuracies, with lacunarity achieving <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>95.04</mn><mo>%</mo><mo>±</mo><mn>6.66</mn><mo>%</mo></mrow></semantics></math></inline-formula>, while deep learning reached <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>95.22</mn><mo>%</mo><mo>±</mo><mn>4.47</mn><mo>%</mo></mrow></semantics></math></inline-formula>. Notably, the highest performance was obtained with <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>2</mn><mo>%</mo></mrow></semantics></math></inline-formula> NaCl, where lacunarity reached <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>97.08</mn><mo>%</mo><mo>±</mo><mn>2.27</mn><mo>%</mo></mrow></semantics></math></inline-formula> and deep learning <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>96.88</mn><mo>%</mo><mo>±</mo><mn>2.8</mn><mo>%</mo></mrow></semantics></math></inline-formula>, indicating improved precision and stability. While deep learning demonstrated more consistent performance across test cases, lacunarity alone captured highly discriminative structural features, making it a valuable complementary tool. The integration of NaCl and lacunarity analysis offers a robust and interpretable methodology for ensuring the quality and authenticity of dairy products, particularly in detecting adulteration, where morphological contrast is less evident.
format Article
id doaj-art-ac3fec317396419a878bfaf50da4bbb8
institution OA Journals
issn 2076-3417
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-ac3fec317396419a878bfaf50da4bbb82025-08-20T01:56:25ZengMDPI AGApplied Sciences2076-34172025-05-011510567610.3390/app15105676Pattern Recognition in Dried Milk Droplets Using Lacunarity and Deep LearningJosías N. Molina-Courtois0Yaquelin Josefa Aguilar Morales1Luis Escalante-Zarate2Mario Castelán3Yojana J. P. Carreón4Jorge González-Gutiérrez5Facultad de Ciencias en Física y Matemáticas, Universidad Autónoma de Chiapas, Tuxtla Gutiérrez 29050, Chiapas, MexicoFacultad de Ciencias en Física y Matemáticas, Universidad Autónoma de Chiapas, Tuxtla Gutiérrez 29050, Chiapas, MexicoFacultad de Ciencias en Física y Matemáticas, Universidad Autónoma de Chiapas, Tuxtla Gutiérrez 29050, Chiapas, MexicoRobotics and Advanced Manufacturing, Center for Research and Advanced Studies of the National Polytechnic Institute, Ramos Arizpe 25900, Coahuila, MexicoFacultad de Ciencias en Física y Matemáticas, Universidad Autónoma de Chiapas, Tuxtla Gutiérrez 29050, Chiapas, MexicoFacultad de Ciencias en Física y Matemáticas, Universidad Autónoma de Chiapas, Tuxtla Gutiérrez 29050, Chiapas, MexicoThis study introduces a novel method for classifying whole and lactose-free milk and the detection of water adulteration through analyzing dried droplets. The key innovation is the addition of NaCl, which modulates crystallization to enhance structural differentiation and facilitate the classification of milk types and detection of adulteration. Dried droplets of milk containing NaCl concentrations of <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>0</mn><mo>%</mo></mrow></semantics></math></inline-formula>, <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>2</mn><mo>%</mo></mrow></semantics></math></inline-formula>, and <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>4</mn><mo>%</mo></mrow></semantics></math></inline-formula> were analyzed, revealing distinct morphologies, including amorphous, cross-shaped, and dendritic crystals. These structures were quantitatively characterized using lacunarity to assess their discriminatory power. Two classification approaches were evaluated: one based on lacunarity analysis alone and another incorporating deep learning. Both methods yielded high classification accuracies, with lacunarity achieving <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>95.04</mn><mo>%</mo><mo>±</mo><mn>6.66</mn><mo>%</mo></mrow></semantics></math></inline-formula>, while deep learning reached <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>95.22</mn><mo>%</mo><mo>±</mo><mn>4.47</mn><mo>%</mo></mrow></semantics></math></inline-formula>. Notably, the highest performance was obtained with <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>2</mn><mo>%</mo></mrow></semantics></math></inline-formula> NaCl, where lacunarity reached <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>97.08</mn><mo>%</mo><mo>±</mo><mn>2.27</mn><mo>%</mo></mrow></semantics></math></inline-formula> and deep learning <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>96.88</mn><mo>%</mo><mo>±</mo><mn>2.8</mn><mo>%</mo></mrow></semantics></math></inline-formula>, indicating improved precision and stability. While deep learning demonstrated more consistent performance across test cases, lacunarity alone captured highly discriminative structural features, making it a valuable complementary tool. The integration of NaCl and lacunarity analysis offers a robust and interpretable methodology for ensuring the quality and authenticity of dairy products, particularly in detecting adulteration, where morphological contrast is less evident.https://www.mdpi.com/2076-3417/15/10/5676lacunaritydeep learningCNNpattern recognitionmilk adulterationdried droplets
spellingShingle Josías N. Molina-Courtois
Yaquelin Josefa Aguilar Morales
Luis Escalante-Zarate
Mario Castelán
Yojana J. P. Carreón
Jorge González-Gutiérrez
Pattern Recognition in Dried Milk Droplets Using Lacunarity and Deep Learning
Applied Sciences
lacunarity
deep learning
CNN
pattern recognition
milk adulteration
dried droplets
title Pattern Recognition in Dried Milk Droplets Using Lacunarity and Deep Learning
title_full Pattern Recognition in Dried Milk Droplets Using Lacunarity and Deep Learning
title_fullStr Pattern Recognition in Dried Milk Droplets Using Lacunarity and Deep Learning
title_full_unstemmed Pattern Recognition in Dried Milk Droplets Using Lacunarity and Deep Learning
title_short Pattern Recognition in Dried Milk Droplets Using Lacunarity and Deep Learning
title_sort pattern recognition in dried milk droplets using lacunarity and deep learning
topic lacunarity
deep learning
CNN
pattern recognition
milk adulteration
dried droplets
url https://www.mdpi.com/2076-3417/15/10/5676
work_keys_str_mv AT josiasnmolinacourtois patternrecognitionindriedmilkdropletsusinglacunarityanddeeplearning
AT yaquelinjosefaaguilarmorales patternrecognitionindriedmilkdropletsusinglacunarityanddeeplearning
AT luisescalantezarate patternrecognitionindriedmilkdropletsusinglacunarityanddeeplearning
AT mariocastelan patternrecognitionindriedmilkdropletsusinglacunarityanddeeplearning
AT yojanajpcarreon patternrecognitionindriedmilkdropletsusinglacunarityanddeeplearning
AT jorgegonzalezgutierrez patternrecognitionindriedmilkdropletsusinglacunarityanddeeplearning