Reconstruct faces and identify tattoos. AI joins the search for the missing in Mexico

In a country with more than 132,000 missing people, Mexico is turning to artificial intelligence to speed up searches and identify victims. From videos that give a “voice” to the missing to systems that analyze tattoos, restore faces or project the aging of children, these tools are transforming the efforts of families, authorities and researchers, although experts stress that technology does not replace human cooperation

In 2021, Héctor Daniel Flores Hernández was reported missing. Two years later, his father, Héctor Flores, saw his son’s image speak again. In a video generated using artificial intelligence technology, which digitally animated a still image and gave it a synthesized voice, the figure of Héctor Daniel Flores Hernández narrated the story of his disappearance — when he was 19 years old, from his home in Guadalajara — and demanded that the authorities find him alive. Since then, the father has made the search a way of life.

“I couldn’t finish watching it the first time,” said Héctor Flores when the video was produced. “It took me a while to process. Seeing them with the last photo we have, saying what we know from the investigations, is devastating.”

The video was part of an initiative launched in 2023 by the collectives Luz de Esperanza and Alas de Libertad — groups of family members of missing people who organize themselves to carry out searches, raise awareness of the cases and demand justice — in the western state of Jalisco, to give voice to the warnings of missing people about their family members. Flores, co-founder of Luz de Esperanza, said that the initiative continues and that “it is a perfect tool not only for searching, but also for raising awareness and trying to create empathy.”

Disappearances are all too common in Mexico, a country that has recorded more than 132,000 missing people since the Interior Secretariat’s National Registry of Missing and Unlocated Persons began collecting data in 1964. It says the government has not taken sufficient measures to prevent disappearances or punish those responsible.

President Claudia Sheinbaum that the majority of disappearances are linked to organized crime, and Amnesty International that the problem can be attributed to widespread violence and insecurity. There are no complete official data on the specific causes of all disappearances; The national registry includes data on past disappearances committed by authorities against left-wing groups and guerrillas, but the numbers are mainly from recent years, when the fight against criminal organizations intensified.

In March 2025, Sheinbaum’s government announced a series of new initiatives to respond more quickly to cases of disappearances, to treat these cases with the same seriousness as confirmed abductions, to make statistics more accessible, and to improve assistance to victims.

The video initiative, however, is part of a new generation of projects that use AI or machine learning to help address the crisis. Universities, research groups, other organizations and government authorities have developed and implemented AI to investigate missing people, using techniques including database analysis, forensic identification or age progression projections.

“The objective is for these tools to be useful for the entities that make up the national search system, such as prosecutors’ offices, commissions and Semefo (Forensic Medical Services), to support and facilitate people’s work”, explained Andrea Horcasitas, responsible for the Human Rights Program at the Universidad Iberoamericana, in Mexico City. The program is part of the Consortium for the Ethical Use of AI in the Search for Missing Persons, created in October 2025 with the aim of discussing the use of techniques to search for missing people in Mexico and reflecting on the responsible use of AI in this area.

AI to identify tattoos

The Public Policy Collaborative Solutions Laboratory (), a non-governmental organization based in Mexico, works to find new solutions to problems of security, violence and access to justice in Latin America. The laboratory has developed three projects that incorporate artificial intelligence in the search for missing people.

The first is IdentIA, a tool that uses AI to identify and classify photographs of tattoos on unidentified bodies, explained Thomas Favennec, executive director of Lab-Co.

Users can search files with text, using words present in a tattoo or a verbal description, or through image-based searches that directly compare photographs with a historical database of tattoos belonging to unidentified people.

“It doesn’t matter the quality of the tattoo or the angle. This system works with a vector search and does not require the internet; no sensitive content is uploaded online, which guarantees that no information is compromised”, explained Ángel Serrano, data and technology coordinator at Lab-Co.

Serrano demonstrated how IdentIA performs a tattoo search in just a few seconds and allows data to be cross-referenced with records of missing people.

This system has been incorporated into the missing persons database systems in the state of Jalisco and is in the process of being implemented in the forensic services of Quintana Roo and Zacatecas.

Search in separate files

Another of the laboratory’s tools, explained Favennec, is ContextIA, which allows processing multiple unstructured documents from investigation processes and extracting clear data. ContextIA is able to answer specific queries with direct citations and page references; extract concrete data such as telephone numbers, license plates and coordinates; and, as the name suggests, cross cases in the context of different databases.

The third tool allows the analysis of names in a structured and more powerful way, allowing you to find matches in different databases where names can be written in different ways. Favennec said that, so far, it has been applied to identified deceased people who have not been claimed.

“Families don’t know that this happens, and it’s complicated because there is a problem with databases that don’t cross,” he said. “There is a challenge in finding the family. Therefore, we developed something that allows comparative analyzes between the situation of missing people and the records of forensic services in different states of the country.”

The initiatives are part of a project called “Building Alliances for the Search for Missing Persons and Human Identification”, funded by the European Union and the British Embassy through the Frontier Tech Hub initiative.

Restore faces of the missing

Horcasitas, from the Universidad Iberoamericana, says that some prosecutors’ offices already use a tool called ImageBox, which improves images of the faces of people found in the morgue or at the Forensic Medical Service and the Institute of Forensic and Expert Sciences in Mexico City, to help identify individuals.

“This prevents people from having to look at devastating photographs, which obviously have psychosocial impacts on anyone having to go through mortuary catalogues,” he said.

The Mexico City Prosecutor’s Office has been using the “inpainting” technique, which uses artificial intelligence to fill, restore or remove selected parts of an image, allowing the addition or repair of damaged areas with realistic results. With this, authorities carry out reverse searches, issuing a bulletin to find the person’s family.

CNN contacted the capital’s prosecutor’s office for more details, but received no response.

Children’s faces grow

The Regresa Project, developed by researchers at the National Autonomous University of Mexico (UNAM), seeks to generate an image of what a child who disappeared years ago would look like today, to help families find them.

When a person goes missing, the default search protocol is based on the most recent photograph available. Children and adolescents who are not quickly located may not be recognized in the medium to long term, due to the speed with which their faces and bodies change and mature.

Led by Ana Itzel Juárez Martín, PhD in anthropology from the National Autonomous University of Mexico (UNAM), the initiative, still in the pilot phase, combines AI tools with knowledge and techniques from physical and social anthropology.

The program’s algorithm was designed to perform age progression using photographs of missing children, determining what they would look like at 5, 15 or 30 years old. It can also be used to show what a current adult was like as a child.

aged 17 or younger reported missing between 1964 and September 2025. A 2022 report by the Network for Children’s Rights in Mexico points out that, in the case of missing minors, recruitment networks can integrate them into organized crime or lead them to sexual exploitation and trafficking.

is to train the algorithm to learn the natural biological growth of the face, guided specifically by facial shapes and growth patterns common among people in Mexico.

“Although there are already some image banks for investigation, there are none exclusively of the Mexican population,” he stated. “Thus, this algorithm would be the first of its kind and would be trained to identify the variability that exists among Mexicans, for example, the type of nose, thickness of the lips, shape of the eyes and eyebrows.”

Cooperate and work faster

In a country where, according to the organization Causa en Común, 41 people disappear every day, it is important to have tools that help and facilitate the search for missing people throughout the territory.

The next step is to continue to identify gaps where certain processes need to be more efficient. “We are waiting to see how these artificial intelligence tools work, to understand if they work, what improvements are necessary and also to understand what the workflow is within the organizations that make up the National Search System”, said Horcasitas.

Favennec highlighted that the implementation of AI in search and location processes has been well received by groups and authorities, but added that it is necessary to realize that the technology “is not magic, it helps to process information faster and better… In a crisis where so many things mix in such different ways, what is needed is collaboration.”