A novel non-destructive terahertz imaging technique has been developed to detect and identify illicit drugs hidden in mail envelopes. The method uses component spatial pattern analysis, which extracts spatial distributions of targets from terahertz multispectral transillumination images. The technique relies on absorption spectra measured with a tunable terahertz-wave source. The study used methamphetamine, MDMA, and aspirin as samples. The THz wave's ability to penetrate various materials and its unique spectral fingerprints make it suitable for drug detection. The system includes a THz-wave parametric oscillator, imaging optics, and a detector. The spatial distribution of drugs was extracted from multispectral images using absorption spectra. The component spatial pattern analysis method allows for the identification of specific drugs by utilizing their unique spectral fingerprints. The results showed that the method can distinguish between methamphetamine, MDMA, and aspirin. The technique has potential applications in drug detection, security screening, and pharmaceutical quality inspection. The study also highlights the need for further research to improve the spatial resolution and speed of the imaging system. The research was supported by a grant from the Japanese Ministry of Education, Science, and Culture.A novel non-destructive terahertz imaging technique has been developed to detect and identify illicit drugs hidden in mail envelopes. The method uses component spatial pattern analysis, which extracts spatial distributions of targets from terahertz multispectral transillumination images. The technique relies on absorption spectra measured with a tunable terahertz-wave source. The study used methamphetamine, MDMA, and aspirin as samples. The THz wave's ability to penetrate various materials and its unique spectral fingerprints make it suitable for drug detection. The system includes a THz-wave parametric oscillator, imaging optics, and a detector. The spatial distribution of drugs was extracted from multispectral images using absorption spectra. The component spatial pattern analysis method allows for the identification of specific drugs by utilizing their unique spectral fingerprints. The results showed that the method can distinguish between methamphetamine, MDMA, and aspirin. The technique has potential applications in drug detection, security screening, and pharmaceutical quality inspection. The study also highlights the need for further research to improve the spatial resolution and speed of the imaging system. The research was supported by a grant from the Japanese Ministry of Education, Science, and Culture.